---
_id: '60990'
abstract:
- lang: eng
text: 'Large Language Models (LLMs) have demonstrated remarkable performance across
a wide range of natural language processing tasks. However, their effectiveness
in low-resource languages remains underexplored, particularly in complex tasks
such as end-to-end Entity Linking (EL), which requires both mention detection
and disambiguation against a knowledge base (KB). In earlier work, we introduced
IndEL — the first end-to-end EL benchmark dataset for the Indonesian language
— covering both a general domain (news) and a specific domain (religious text
from the Indonesian translation of the Quran), and evaluated four traditional
end-to-end EL systems on this dataset. In this study, we propose ELEVATE-ID, a
comprehensive evaluation framework for assessing LLM performance on end-to-end
EL in Indonesian. The framework evaluates LLMs under both zero-shot and fine-tuned
conditions, using multilingual and Indonesian monolingual models, with Wikidata
as the target KB. Our experiments include performance benchmarking, generalization
analysis across domains, and systematic error analysis. Results show that GPT-4
and GPT-3.5 achieve the highest accuracy in zero-shot and fine-tuned settings,
respectively. However, even fine-tuned GPT-3.5 underperforms compared to DBpedia
Spotlight — the weakest of the traditional model baselines — in the general domain.
Interestingly, GPT-3.5 outperforms Babelfy in the specific domain. Generalization
analysis indicates that fine-tuned GPT-3.5 adapts more effectively to cross-domain
and mixed-domain scenarios. Error analysis uncovers persistent challenges that
hinder LLM performance: difficulties with non-complete mentions, acronym disambiguation,
and full-name recognition in formal contexts. These issues point to limitations
in mention boundary detection and contextual grounding. Indonesian-pretrained
LLMs, Komodo and Merak, reveal core weaknesses: template leakage and entity hallucination,
respectively—underscoring architectural and training limitations in low-resource
end-to-end EL.11Code and dataset are available at https://github.com/dice-group/ELEVATE-ID.'
article_type: original
author:
- first_name: Ria Hari
full_name: Gusmita, Ria Hari
id: '71039'
last_name: Gusmita
- first_name: Asep Fajar
full_name: Firmansyah, Asep Fajar
id: '76787'
last_name: Firmansyah
- first_name: Hamada Mohamed Abdelsamee
full_name: Zahera, Hamada Mohamed Abdelsamee
id: '72768'
last_name: Zahera
orcid: 0000-0003-0215-1278
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Gusmita RH, Firmansyah AF, Zahera HMA, Ngonga Ngomo A-C. ELEVATE-ID: Extending
Large Language Models for End-to-End Entity Linking Evaluation in Indonesian.
Data & Knowledge Engineering. 2026;161:102504. doi:https://doi.org/10.1016/j.datak.2025.102504'
apa: 'Gusmita, R. H., Firmansyah, A. F., Zahera, H. M. A., & Ngonga Ngomo, A.-C.
(2026). ELEVATE-ID: Extending Large Language Models for End-to-End Entity Linking
Evaluation in Indonesian. Data & Knowledge Engineering, 161,
102504. https://doi.org/10.1016/j.datak.2025.102504'
bibtex: '@article{Gusmita_Firmansyah_Zahera_Ngonga Ngomo_2026, title={ELEVATE-ID:
Extending Large Language Models for End-to-End Entity Linking Evaluation in Indonesian},
volume={161}, DOI={https://doi.org/10.1016/j.datak.2025.102504},
journal={Data & Knowledge Engineering}, author={Gusmita, Ria Hari and Firmansyah,
Asep Fajar and Zahera, Hamada Mohamed Abdelsamee and Ngonga Ngomo, Axel-Cyrille},
year={2026}, pages={102504} }'
chicago: 'Gusmita, Ria Hari, Asep Fajar Firmansyah, Hamada Mohamed Abdelsamee Zahera,
and Axel-Cyrille Ngonga Ngomo. “ELEVATE-ID: Extending Large Language Models for
End-to-End Entity Linking Evaluation in Indonesian.” Data & Knowledge Engineering
161 (2026): 102504. https://doi.org/10.1016/j.datak.2025.102504.'
ieee: 'R. H. Gusmita, A. F. Firmansyah, H. M. A. Zahera, and A.-C. Ngonga Ngomo,
“ELEVATE-ID: Extending Large Language Models for End-to-End Entity Linking Evaluation
in Indonesian,” Data & Knowledge Engineering, vol. 161, p. 102504,
2026, doi: https://doi.org/10.1016/j.datak.2025.102504.'
mla: 'Gusmita, Ria Hari, et al. “ELEVATE-ID: Extending Large Language Models for
End-to-End Entity Linking Evaluation in Indonesian.” Data & Knowledge Engineering,
vol. 161, 2026, p. 102504, doi:https://doi.org/10.1016/j.datak.2025.102504.'
short: R.H. Gusmita, A.F. Firmansyah, H.M.A. Zahera, A.-C. Ngonga Ngomo, Data &
Knowledge Engineering 161 (2026) 102504.
date_created: 2025-08-24T11:38:51Z
date_updated: 2025-08-25T09:40:13Z
department:
- _id: '574'
doi: https://doi.org/10.1016/j.datak.2025.102504
intvolume: ' 161'
keyword:
- LLMs
- Evaluation
- End-to-end EL
- Indonesian
language:
- iso: eng
main_file_link:
- url: https://www.sciencedirect.com/science/article/pii/S0169023X25000990?utm_campaign=STMJ_220042_AUTH_SERV_PA&utm_medium=email&utm_acid=78351008&SIS_ID=&dgcid=STMJ_220042_AUTH_SERV_PA&CMX_ID=&utm_in=DM591673&utm_source=AC_
page: '102504'
publication: Data & Knowledge Engineering
publication_identifier:
issn:
- 0169-023X
status: public
title: 'ELEVATE-ID: Extending Large Language Models for End-to-End Entity Linking
Evaluation in Indonesian'
type: journal_article
user_id: '71039'
volume: 161
year: '2026'
...
---
_id: '62721'
abstract:
- lang: eng
text: We introduce the notion of contrastive ABox explanations to answer questions
of the type "Why is a an instance of C, but b is not?". While there are various
approaches for explaining positive entailments (why is C(a) entailed by the knowledge
base) as well as missing entailments (why is C(b) not entailed) in isolation,
contrastive explanations consider both at the same time, which allows them to
focus on the relevant commonalities and differences between a and b. We develop
an appropriate notion of contrastive explanations for the special case of ABox
reasoning with description logic ontologies, and analyze the computational complexity
for different variants under different optimality criteria, considering lightweight
as well as more expressive description logics. We implemented a first method for
computing one variant of contrastive explanations, and evaluated it on generated
problems for realistic knowledge bases.
author:
- first_name: Patrick
full_name: Koopmann, Patrick
last_name: Koopmann
- first_name: Yasir
full_name: Mahmood, Yasir
id: '99353'
last_name: Mahmood
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: Balram
full_name: Tiwari, Balram
last_name: Tiwari
citation:
ama: Koopmann P, Mahmood Y, Ngonga Ngomo A-C, Tiwari B. Can You Tell the Difference?
Contrastive Explanations for ABox Entailments. Pre-print of paper accepted
at AAAI 2026. Published online 2026.
apa: Koopmann, P., Mahmood, Y., Ngonga Ngomo, A.-C., & Tiwari, B. (2026). Can
You Tell the Difference? Contrastive Explanations for ABox Entailments. In Pre-print
of paper accepted at AAAI 2026.
bibtex: '@article{Koopmann_Mahmood_Ngonga Ngomo_Tiwari_2026, title={Can You Tell
the Difference? Contrastive Explanations for ABox Entailments}, journal={Pre-print
of paper accepted at AAAI 2026}, author={Koopmann, Patrick and Mahmood, Yasir
and Ngonga Ngomo, Axel-Cyrille and Tiwari, Balram}, year={2026} }'
chicago: Koopmann, Patrick, Yasir Mahmood, Axel-Cyrille Ngonga Ngomo, and Balram
Tiwari. “Can You Tell the Difference? Contrastive Explanations for ABox Entailments.”
Pre-Print of Paper Accepted at AAAI 2026, 2026.
ieee: P. Koopmann, Y. Mahmood, A.-C. Ngonga Ngomo, and B. Tiwari, “Can You Tell
the Difference? Contrastive Explanations for ABox Entailments,” Pre-print of
paper accepted at AAAI 2026. 2026.
mla: Koopmann, Patrick, et al. “Can You Tell the Difference? Contrastive Explanations
for ABox Entailments.” Pre-Print of Paper Accepted at AAAI 2026, 2026.
short: P. Koopmann, Y. Mahmood, A.-C. Ngonga Ngomo, B. Tiwari, Pre-Print of Paper
Accepted at AAAI 2026 (2026).
date_created: 2025-12-01T12:03:06Z
date_updated: 2025-12-04T21:08:32Z
department:
- _id: '574'
external_id:
arxiv:
- '2511.11281'
language:
- iso: eng
publication: Pre-print of paper accepted at AAAI 2026
status: public
title: Can You Tell the Difference? Contrastive Explanations for ABox Entailments
type: preprint
user_id: '99353'
year: '2026'
...
---
_id: '61325'
author:
- first_name: Anna-Lisa
full_name: Vollmer, Anna-Lisa
last_name: Vollmer
- first_name: Heike M.
full_name: Buhl, Heike M.
id: '27152'
last_name: Buhl
- first_name: Rachid
full_name: Alami, Rachid
last_name: Alami
- first_name: Kary
full_name: Främling, Kary
last_name: Främling
- first_name: Angela
full_name: Grimminger, Angela
id: '57578'
last_name: Grimminger
- first_name: Meisam
full_name: Booshehri, Meisam
last_name: Booshehri
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Vollmer A-L, Buhl HM, Alami R, et al. Components of an explanation for co-constructive
sXAI. In: Rohlfing KJ, Främling K, Lim B, Alpsancar S, Thommes K, eds. Social
Explainable AI. Springer; 2026:39-53. doi:10.1007/978-981-96-5290-7_3'
apa: Vollmer, A.-L., Buhl, H. M., Alami, R., Främling, K., Grimminger, A., Booshehri,
M., & Ngonga Ngomo, A.-C. (2026). Components of an explanation for co-constructive
sXAI. In K. J. Rohlfing, K. Främling, B. Lim, S. Alpsancar, & K. Thommes (Eds.),
Social Explainable AI (pp. 39–53). Springer. https://doi.org/10.1007/978-981-96-5290-7_3
bibtex: '@inbook{Vollmer_Buhl_Alami_Främling_Grimminger_Booshehri_Ngonga Ngomo_2026,
title={Components of an explanation for co-constructive sXAI}, DOI={10.1007/978-981-96-5290-7_3},
booktitle={Social Explainable AI}, publisher={Springer}, author={Vollmer, Anna-Lisa
and Buhl, Heike M. and Alami, Rachid and Främling, Kary and Grimminger, Angela
and Booshehri, Meisam and Ngonga Ngomo, Axel-Cyrille}, editor={Rohlfing, Katharina
J. and Främling, Kary and Lim, Brian and Alpsancar, Suzana and Thommes, Kirsten},
year={2026}, pages={39–53} }'
chicago: Vollmer, Anna-Lisa, Heike M. Buhl, Rachid Alami, Kary Främling, Angela
Grimminger, Meisam Booshehri, and Axel-Cyrille Ngonga Ngomo. “Components of an
Explanation for Co-Constructive SXAI.” In Social Explainable AI, edited
by Katharina J. Rohlfing, Kary Främling, Brian Lim, Suzana Alpsancar, and Kirsten
Thommes, 39–53. Springer, 2026. https://doi.org/10.1007/978-981-96-5290-7_3.
ieee: A.-L. Vollmer et al., “Components of an explanation for co-constructive
sXAI,” in Social Explainable AI, K. J. Rohlfing, K. Främling, B. Lim, S.
Alpsancar, and K. Thommes, Eds. Springer, 2026, pp. 39–53.
mla: Vollmer, Anna-Lisa, et al. “Components of an Explanation for Co-Constructive
SXAI.” Social Explainable AI, edited by Katharina J. Rohlfing et al., Springer,
2026, pp. 39–53, doi:10.1007/978-981-96-5290-7_3.
short: 'A.-L. Vollmer, H.M. Buhl, R. Alami, K. Främling, A. Grimminger, M. Booshehri,
A.-C. Ngonga Ngomo, in: K.J. Rohlfing, K. Främling, B. Lim, S. Alpsancar, K. Thommes
(Eds.), Social Explainable AI, Springer, 2026, pp. 39–53.'
date_created: 2025-09-17T10:16:52Z
date_updated: 2026-03-23T18:28:01Z
department:
- _id: '660'
doi: 10.1007/978-981-96-5290-7_3
editor:
- first_name: Katharina J.
full_name: Rohlfing, Katharina J.
last_name: Rohlfing
- first_name: Kary
full_name: Främling, Kary
last_name: Främling
- first_name: Brian
full_name: Lim, Brian
last_name: Lim
- first_name: Suzana
full_name: Alpsancar, Suzana
last_name: Alpsancar
- first_name: Kirsten
full_name: Thommes, Kirsten
last_name: Thommes
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://link.springer.com/chapter/10.1007/978-981-96-5290-7_3
oa: '1'
page: 39-53
project:
- _id: '112'
name: 'TRR 318; TP A02: Verstehensprozess einer Erklärung beobachten und auswerten'
- _id: '111'
name: 'TRR 318; TP A01: Adaptives Erklären'
- _id: '114'
name: 'TRR 318; TP A04: Integration des technischen Modells in das Partnermodell
bei der Erklärung von digitalen Artefakten'
- _id: '123'
name: TRR 318 - Subproject B5
- _id: '118'
name: 'TRR 318: Project Area INF'
publication: Social Explainable AI
publication_identifier:
eisbn:
- 978-981-96-5290-7
publication_status: epub_ahead
publisher: Springer
quality_controlled: '1'
related_material:
link:
- relation: original
url: https://link.springer.com/chapter/10.1007/978-981-96-5290-7_3
status: public
title: Components of an explanation for co-constructive sXAI
type: book_chapter
user_id: '90826'
year: '2026'
...
---
_id: '65494'
author:
- first_name: Ali
full_name: Manzoor, Ali
id: '77309'
last_name: Manzoor
orcid: https://orcid.org/0000-0001-8403-5160
- first_name: Hammada M.
full_name: Zahera, Hammada M.
last_name: Zahera
- first_name: Muhammad
full_name: Saleem, Muhammad
last_name: Saleem
- first_name: Yasir
full_name: Mahmood, Yasir
id: '99353'
last_name: Mahmood
- first_name: René
full_name: Speck, René
id: '70843'
last_name: Speck
- first_name: Hashim
full_name: Khan, Hashim
id: '76510'
last_name: Khan
orcid: 0009-0006-5953-480X
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Manzoor A, Zahera HM, Saleem M, et al. Document-level Relation Extraction
using Reinforcement Learning with Knowledge Graph Feedback. In: The Semantic
Web – 23rd European Semantic Web Conference, ESWC 2026, Dubrovnik , Croatia, May
10-14, 2026, Proceedings. ; 2026.'
apa: Manzoor, A., Zahera, H. M., Saleem, M., Mahmood, Y., Speck, R., Khan, H., &
Ngonga Ngomo, A.-C. (2026). Document-level Relation Extraction using Reinforcement
Learning with Knowledge Graph Feedback. The Semantic Web – 23rd European Semantic
Web Conference, ESWC 2026, Dubrovnik , Croatia, May 10-14, 2026, Proceedings.
bibtex: '@inproceedings{Manzoor_Zahera_Saleem_Mahmood_Speck_Khan_Ngonga Ngomo_2026,
title={Document-level Relation Extraction using Reinforcement Learning with Knowledge
Graph Feedback}, booktitle={The Semantic Web – 23rd European Semantic Web Conference,
ESWC 2026, Dubrovnik , Croatia, May 10-14, 2026, Proceedings}, author={Manzoor,
Ali and Zahera, Hammada M. and Saleem, Muhammad and Mahmood, Yasir and Speck,
René and Khan, Hashim and Ngonga Ngomo, Axel-Cyrille}, year={2026} }'
chicago: Manzoor, Ali, Hammada M. Zahera, Muhammad Saleem, Yasir Mahmood, René Speck,
Hashim Khan, and Axel-Cyrille Ngonga Ngomo. “Document-Level Relation Extraction
Using Reinforcement Learning with Knowledge Graph Feedback.” In The Semantic
Web – 23rd European Semantic Web Conference, ESWC 2026, Dubrovnik , Croatia, May
10-14, 2026, Proceedings, 2026.
ieee: A. Manzoor et al., “Document-level Relation Extraction using Reinforcement
Learning with Knowledge Graph Feedback,” 2026.
mla: Manzoor, Ali, et al. “Document-Level Relation Extraction Using Reinforcement
Learning with Knowledge Graph Feedback.” The Semantic Web – 23rd European Semantic
Web Conference, ESWC 2026, Dubrovnik , Croatia, May 10-14, 2026, Proceedings,
2026.
short: 'A. Manzoor, H.M. Zahera, M. Saleem, Y. Mahmood, R. Speck, H. Khan, A.-C.
Ngonga Ngomo, in: The Semantic Web – 23rd European Semantic Web Conference, ESWC
2026, Dubrovnik , Croatia, May 10-14, 2026, Proceedings, 2026.'
date_created: 2026-04-23T23:11:26Z
date_updated: 2026-04-23T23:14:33Z
department:
- _id: '504'
keyword:
- dice hamada hashim kiakadamie mahmood manzoor ngonga rene sail saleem
language:
- iso: eng
project:
- _id: '285'
name: SAIL - Nachhaltiger Lebenszyklus von intelligenten soziotechnischen Systemen
publication: The Semantic Web – 23rd European Semantic Web Conference, ESWC 2026,
Dubrovnik , Croatia, May 10-14, 2026, Proceedings
status: public
title: Document-level Relation Extraction using Reinforcement Learning with Knowledge
Graph Feedback
type: conference
user_id: '77309'
year: '2026'
...
---
_id: '65567'
abstract:
- lang: eng
text: "We introduce the notion of contrastive ABox explanations to answer
questions of the type “Why is a an instance of C, but b is not?”. While there
are various approaches for explaining positive entailments (why is C(a) entailed
by the knowledge base) as well as missing entailments (why is C(b) not entailed)
in isolation, contrastive explanations consider both at the same time, which allows
them to focus on the relevant commonalities and differences between a and b. We
develop an appropriate notion of contrastive explanations for the special case
of ABox reasoning with description logic ontologies, and analyze the computational
complexity for different variants under different optimality criteria, considering
lightweight as well as more expressive description logics. We\r\nimplemented a
first method for computing one variant of contrastive explanations, and evaluated
it on generated problems for realistic knowledge bases."
author:
- first_name: Patrick
full_name: Koopmann, Patrick
last_name: Koopmann
- first_name: Yasir
full_name: Mahmood, Yasir
id: '99353'
last_name: Mahmood
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: Balram
full_name: Tiwari, Balram
last_name: Tiwari
citation:
ama: 'Koopmann P, Mahmood Y, Ngonga Ngomo A-C, Tiwari B. Can You Tell the Difference?
Contrastive Explanations for ABox Entailments. In: Proceedings of the AAAI
Conference on Artificial Intelligence. Vol 40. Association for the Advancement
of Artificial Intelligence (AAAI); 2026:19189-19197. doi:10.1609/aaai.v40i23.38993'
apa: Koopmann, P., Mahmood, Y., Ngonga Ngomo, A.-C., & Tiwari, B. (2026). Can
You Tell the Difference? Contrastive Explanations for ABox Entailments. Proceedings
of the AAAI Conference on Artificial Intelligence, 40(23), 19189–19197.
https://doi.org/10.1609/aaai.v40i23.38993
bibtex: '@inproceedings{Koopmann_Mahmood_Ngonga Ngomo_Tiwari_2026, title={Can You
Tell the Difference? Contrastive Explanations for ABox Entailments}, volume={40},
DOI={10.1609/aaai.v40i23.38993},
number={23}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
publisher={Association for the Advancement of Artificial Intelligence (AAAI)},
author={Koopmann, Patrick and Mahmood, Yasir and Ngonga Ngomo, Axel-Cyrille and
Tiwari, Balram}, year={2026}, pages={19189–19197} }'
chicago: Koopmann, Patrick, Yasir Mahmood, Axel-Cyrille Ngonga Ngomo, and Balram
Tiwari. “Can You Tell the Difference? Contrastive Explanations for ABox Entailments.”
In Proceedings of the AAAI Conference on Artificial Intelligence, 40:19189–97.
Association for the Advancement of Artificial Intelligence (AAAI), 2026. https://doi.org/10.1609/aaai.v40i23.38993.
ieee: 'P. Koopmann, Y. Mahmood, A.-C. Ngonga Ngomo, and B. Tiwari, “Can You Tell
the Difference? Contrastive Explanations for ABox Entailments,” in Proceedings
of the AAAI Conference on Artificial Intelligence, 2026, vol. 40, no. 23,
pp. 19189–19197, doi: 10.1609/aaai.v40i23.38993.'
mla: Koopmann, Patrick, et al. “Can You Tell the Difference? Contrastive Explanations
for ABox Entailments.” Proceedings of the AAAI Conference on Artificial Intelligence,
vol. 40, no. 23, Association for the Advancement of Artificial Intelligence (AAAI),
2026, pp. 19189–97, doi:10.1609/aaai.v40i23.38993.
short: 'P. Koopmann, Y. Mahmood, A.-C. Ngonga Ngomo, B. Tiwari, in: Proceedings
of the AAAI Conference on Artificial Intelligence, Association for the Advancement
of Artificial Intelligence (AAAI), 2026, pp. 19189–19197.'
date_created: 2026-05-05T15:15:49Z
date_updated: 2026-05-05T15:22:12Z
department:
- _id: '574'
doi: 10.1609/aaai.v40i23.38993
intvolume: ' 40'
issue: '23'
language:
- iso: eng
page: 19189-19197
project:
- _id: '117'
name: TRR 318 - Project Area C
publication: Proceedings of the AAAI Conference on Artificial Intelligence
publication_identifier:
issn:
- 2374-3468
- 2159-5399
publication_status: published
publisher: Association for the Advancement of Artificial Intelligence (AAAI)
status: public
title: Can You Tell the Difference? Contrastive Explanations for ABox Entailments
type: conference
user_id: '99353'
volume: 40
year: '2026'
...
---
_id: '54450'
abstract:
- lang: eng
text: In the last decade, there has been increasing interest in allowing users to
understand how the predictions of machine-learned models come about, thus increasing
transparency and empowering users to understand and potentially contest those
decisions.Dialogue-based approaches, in contrast to traditional one-shot eXplainable
Artificial Intelligence (XAI) methods, facilitate interactive, in-depth exploration
through multi-turn dialogues, simulating expert conversations. This paper reviews
the current state of dialogue-based XAI, presenting a systematic review of 1,339
publications, narrowed down to 14 based on inclusion criteria. We explore theoretical
foundations of the systems, propose key dimensions along which different solutions
to dialogue-based XAI differ, and identify key use cases, target audiences, system
components, and the types of supported queries and responses. Furthermore, we
investigate the current paradigms by which systems are evaluated and highlight
their key limitations. Key findings include identifying the main use cases, objectives,
and audiences targeted by dialogue-based XAI methods, and summarize the main types
of questions and information needs. Beyond discussing avenues for future work,
we present a meta-architecture for these systems from existing literature and
outlined prevalent theoretical frameworks.
article_number: '81'
author:
- first_name: Dimitry
full_name: Mindlin, Dimitry
last_name: Mindlin
- first_name: Fabian
full_name: Beer, Fabian
last_name: Beer
- first_name: Leonie Nora
full_name: Sieger, Leonie Nora
id: '93402'
last_name: Sieger
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Philipp
full_name: Cimiano, Philipp
last_name: Cimiano
- first_name: Elena
full_name: Esposito, Elena
last_name: Esposito
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Mindlin D, Beer F, Sieger LN, et al. Beyond One-Shot Explanations: A Systematic
Literature Review of Dialogue-Based XAI Approaches. Artificial Intelligence
Review. 2025;58(3). doi:10.1007/s10462-024-11007-7'
apa: 'Mindlin, D., Beer, F., Sieger, L. N., Heindorf, S., Cimiano, P., Esposito,
E., & Ngonga Ngomo, A.-C. (2025). Beyond One-Shot Explanations: A Systematic
Literature Review of Dialogue-Based XAI Approaches. Artificial Intelligence
Review, 58(3), Article 81. https://doi.org/10.1007/s10462-024-11007-7'
bibtex: '@article{Mindlin_Beer_Sieger_Heindorf_Cimiano_Esposito_Ngonga Ngomo_2025,
title={Beyond One-Shot Explanations: A Systematic Literature Review of Dialogue-Based
XAI Approaches}, volume={58}, DOI={10.1007/s10462-024-11007-7},
number={381}, journal={Artificial Intelligence Review}, publisher={Springer},
author={Mindlin, Dimitry and Beer, Fabian and Sieger, Leonie Nora and Heindorf,
Stefan and Cimiano, Philipp and Esposito, Elena and Ngonga Ngomo, Axel-Cyrille},
year={2025} }'
chicago: 'Mindlin, Dimitry, Fabian Beer, Leonie Nora Sieger, Stefan Heindorf, Philipp
Cimiano, Elena Esposito, and Axel-Cyrille Ngonga Ngomo. “Beyond One-Shot Explanations:
A Systematic Literature Review of Dialogue-Based XAI Approaches.” Artificial
Intelligence Review 58, no. 3 (2025). https://doi.org/10.1007/s10462-024-11007-7.'
ieee: 'D. Mindlin et al., “Beyond One-Shot Explanations: A Systematic Literature
Review of Dialogue-Based XAI Approaches,” Artificial Intelligence Review,
vol. 58, no. 3, Art. no. 81, 2025, doi: 10.1007/s10462-024-11007-7.'
mla: 'Mindlin, Dimitry, et al. “Beyond One-Shot Explanations: A Systematic Literature
Review of Dialogue-Based XAI Approaches.” Artificial Intelligence Review,
vol. 58, no. 3, 81, Springer, 2025, doi:10.1007/s10462-024-11007-7.'
short: D. Mindlin, F. Beer, L.N. Sieger, S. Heindorf, P. Cimiano, E. Esposito, A.-C.
Ngonga Ngomo, Artificial Intelligence Review 58 (2025).
date_created: 2024-05-26T18:55:58Z
date_updated: 2025-01-24T20:09:20Z
department:
- _id: '760'
- _id: '574'
doi: 10.1007/s10462-024-11007-7
intvolume: ' 58'
issue: '3'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://link.springer.com/article/10.1007/s10462-024-11007-7
oa: '1'
publication: Artificial Intelligence Review
publication_status: published
publisher: Springer
status: public
title: 'Beyond One-Shot Explanations: A Systematic Literature Review of Dialogue-Based
XAI Approaches'
type: journal_article
user_id: '11871'
volume: 58
year: '2025'
...
---
_id: '59910'
abstract:
- lang: eng
text: The connection between inconsistent databases and Dung’s abstract
argumentation framework has recently drawn growing interest. Specifically, an
inconsistent database, involving certain types of integrity constraints such as
functional and inclusion dependencies, can be viewed as an argumentation framework
in Dung’s setting. Nevertheless, no prior work has explored the exact expressive
power of Dung’s theory of argumentation when compared to inconsistent databases
and integrity constraints. In this paper, we close this gap by arguing that an
argumentation framework can also be viewed as an inconsistent database. We first
establish a connection between subset-repairs for databases and extensions for
AFs considering conflict-free, naive, admissible, and preferred semantics. Further,
we define a new family of attribute-based repairs based on the principle of maximal
content preservation. The effectiveness of these repairs is then highlighted by
connecting them to stable, semi-stable, and stage semantics. Our main contributions
include translating an argumentation framework into a database together with integrity
constraints. Moreover, this translation can be achieved in polynomial time, which
is essential in transferring complexity results between the two formalisms.
author:
- first_name: Yasir
full_name: Mahmood, Yasir
id: '99353'
last_name: Mahmood
- first_name: Markus
full_name: Hecher, Markus
last_name: Hecher
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Mahmood Y, Hecher M, Ngonga Ngomo A-C. Dung’s Argumentation Framework: Unveiling
the Expressive Power with Inconsistent Databases. In: Proceedings of the AAAI
Conference on Artificial Intelligence. Vol 39. Association for the Advancement
of Artificial Intelligence (AAAI); 2025:15058-15066. doi:10.1609/aaai.v39i14.33651'
apa: 'Mahmood, Y., Hecher, M., & Ngonga Ngomo, A.-C. (2025). Dung’s Argumentation
Framework: Unveiling the Expressive Power with Inconsistent Databases. Proceedings
of the AAAI Conference on Artificial Intelligence, 39(14), 15058–15066.
https://doi.org/10.1609/aaai.v39i14.33651'
bibtex: '@inproceedings{Mahmood_Hecher_Ngonga Ngomo_2025, title={Dung’s Argumentation
Framework: Unveiling the Expressive Power with Inconsistent Databases}, volume={39},
DOI={10.1609/aaai.v39i14.33651},
number={14}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
publisher={Association for the Advancement of Artificial Intelligence (AAAI)},
author={Mahmood, Yasir and Hecher, Markus and Ngonga Ngomo, Axel-Cyrille}, year={2025},
pages={15058–15066} }'
chicago: 'Mahmood, Yasir, Markus Hecher, and Axel-Cyrille Ngonga Ngomo. “Dung’s
Argumentation Framework: Unveiling the Expressive Power with Inconsistent Databases.”
In Proceedings of the AAAI Conference on Artificial Intelligence, 39:15058–66.
Association for the Advancement of Artificial Intelligence (AAAI), 2025. https://doi.org/10.1609/aaai.v39i14.33651.'
ieee: 'Y. Mahmood, M. Hecher, and A.-C. Ngonga Ngomo, “Dung’s Argumentation Framework:
Unveiling the Expressive Power with Inconsistent Databases,” in Proceedings
of the AAAI Conference on Artificial Intelligence, 2025, vol. 39, no. 14,
pp. 15058–15066, doi: 10.1609/aaai.v39i14.33651.'
mla: 'Mahmood, Yasir, et al. “Dung’s Argumentation Framework: Unveiling the Expressive
Power with Inconsistent Databases.” Proceedings of the AAAI Conference on Artificial
Intelligence, vol. 39, no. 14, Association for the Advancement of Artificial
Intelligence (AAAI), 2025, pp. 15058–66, doi:10.1609/aaai.v39i14.33651.'
short: 'Y. Mahmood, M. Hecher, A.-C. Ngonga Ngomo, in: Proceedings of the AAAI Conference
on Artificial Intelligence, Association for the Advancement of Artificial Intelligence
(AAAI), 2025, pp. 15058–15066.'
date_created: 2025-05-15T11:05:36Z
date_updated: 2026-02-20T10:07:00Z
department:
- _id: '574'
doi: 10.1609/aaai.v39i14.33651
intvolume: ' 39'
issue: '14'
language:
- iso: eng
page: 15058-15066
project:
- _id: '121'
name: 'TRR 318; TP B01: Ein dialogbasierter Ansatz zur Erklärung von Modellen des
maschinellen Lernens'
publication: Proceedings of the AAAI Conference on Artificial Intelligence
publication_identifier:
issn:
- 2374-3468
- 2159-5399
publication_status: published
publisher: Association for the Advancement of Artificial Intelligence (AAAI)
status: public
title: 'Dung’s Argumentation Framework: Unveiling the Expressive Power with Inconsistent
Databases'
type: conference
user_id: '99353'
volume: 39
year: '2025'
...
---
_id: '63027'
author:
- first_name: Reda
full_name: Ihtassine, Reda
id: '103911'
last_name: Ihtassine
- first_name: Asep Fajar
full_name: Firmansyah, Asep Fajar
id: '76787'
last_name: Firmansyah
- first_name: Nikit
full_name: Srivastava, Nikit
id: '70066'
last_name: Srivastava
orcid: 0009-0004-5164-4911
- first_name: Ali
full_name: Manzoor, Ali
id: '77309'
last_name: Manzoor
orcid: https://orcid.org/0000-0001-8403-5160
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: Mohamed Ahmed
full_name: Sherif, Mohamed Ahmed
last_name: Sherif
citation:
ama: 'Ihtassine R, Firmansyah AF, Srivastava N, Manzoor A, Ngonga Ngomo A-C, Sherif
MA. NL2LS: LLM-based Automatic Linking of Knowledge Graphs. In: Proceedings
of the Knowledge Capture Conference 2025. ACM; 2025. doi:10.1145/3731443.3771374'
apa: 'Ihtassine, R., Firmansyah, A. F., Srivastava, N., Manzoor, A., Ngonga Ngomo,
A.-C., & Sherif, M. A. (2025). NL2LS: LLM-based Automatic Linking of Knowledge
Graphs. Proceedings of the Knowledge Capture Conference 2025. https://doi.org/10.1145/3731443.3771374'
bibtex: '@inproceedings{Ihtassine_Firmansyah_Srivastava_Manzoor_Ngonga Ngomo_Sherif_2025,
title={NL2LS: LLM-based Automatic Linking of Knowledge Graphs}, DOI={10.1145/3731443.3771374},
booktitle={Proceedings of the Knowledge Capture Conference 2025}, publisher={ACM},
author={Ihtassine, Reda and Firmansyah, Asep Fajar and Srivastava, Nikit and Manzoor,
Ali and Ngonga Ngomo, Axel-Cyrille and Sherif, Mohamed Ahmed}, year={2025} }'
chicago: 'Ihtassine, Reda, Asep Fajar Firmansyah, Nikit Srivastava, Ali Manzoor,
Axel-Cyrille Ngonga Ngomo, and Mohamed Ahmed Sherif. “NL2LS: LLM-Based Automatic
Linking of Knowledge Graphs.” In Proceedings of the Knowledge Capture Conference
2025. ACM, 2025. https://doi.org/10.1145/3731443.3771374.'
ieee: 'R. Ihtassine, A. F. Firmansyah, N. Srivastava, A. Manzoor, A.-C. Ngonga Ngomo,
and M. A. Sherif, “NL2LS: LLM-based Automatic Linking of Knowledge Graphs,” 2025,
doi: 10.1145/3731443.3771374.'
mla: 'Ihtassine, Reda, et al. “NL2LS: LLM-Based Automatic Linking of Knowledge Graphs.”
Proceedings of the Knowledge Capture Conference 2025, ACM, 2025, doi:10.1145/3731443.3771374.'
short: 'R. Ihtassine, A.F. Firmansyah, N. Srivastava, A. Manzoor, A.-C. Ngonga Ngomo,
M.A. Sherif, in: Proceedings of the Knowledge Capture Conference 2025, ACM, 2025.'
date_created: 2025-12-10T17:19:20Z
date_updated: 2026-03-09T12:42:07Z
doi: 10.1145/3731443.3771374
language:
- iso: eng
publication: Proceedings of the Knowledge Capture Conference 2025
publication_status: published
publisher: ACM
status: public
title: 'NL2LS: LLM-based Automatic Linking of Knowledge Graphs'
type: conference
user_id: '77309'
year: '2025'
...
---
_id: '57324'
abstract:
- lang: eng
text: Generating SPARQL queries is crucial for extracting relevant information from
diverse knowledge graphs. However, the structural and semantic differences among
these graphs necessitate training or fine-tuning a tailored model for each one.
In this paper, we propose UniQ-Gen, a unified query generation approach to generate
SPARQL queries across various knowledge graphs. UniQ-Gen integrates entity recognition,
disambiguation, and linking through a BERT-NER model and employs cross-encoder
ranking to align questions with the Freebase ontology. We conducted several experiments
on different benchmark datasets such as LC-QuAD 2.0, GrailQA, and QALD-10. The
evaluation results demonstrate that our approach achieves performance equivalent
to or better than models fine-tuned for individual knowledge graphs. This finding
suggests that fine-tuning a unified model on a heterogeneous dataset of SPARQL
queries across different knowledge graphs eliminates the need for separate models
for each graph, thereby reducing resource requirements.
author:
- first_name: Daniel
full_name: Vollmers, Daniel
last_name: Vollmers
- first_name: Nikit
full_name: Srivastava, Nikit
id: '70066'
last_name: Srivastava
orcid: 0009-0004-5164-4911
- first_name: Hamada Mohamed Abdelsamee
full_name: Zahera, Hamada Mohamed Abdelsamee
id: '72768'
last_name: Zahera
orcid: 0000-0003-0215-1278
- first_name: Diego
full_name: Moussallem, Diego
id: '71635'
last_name: Moussallem
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Vollmers D, Srivastava N, Zahera HMA, Moussallem D, Ngonga Ngomo A-C. UniQ-Gen:
Unified Query Generation Across Multiple Knowledge Graphs. In: Alam M, Rospocher
M, van Erp M, Hollink L, Gesese GA, eds. Knowledge Engineering and Knowledge
Management. Springer Nature Switzerland; 2025:174–189. doi:https://doi.org/10.1007/978-3-031-77792-9_11'
apa: 'Vollmers, D., Srivastava, N., Zahera, H. M. A., Moussallem, D., & Ngonga
Ngomo, A.-C. (2025). UniQ-Gen: Unified Query Generation Across Multiple Knowledge
Graphs. In M. Alam, M. Rospocher, M. van Erp, L. Hollink, & G. A. Gesese (Eds.),
Knowledge Engineering and Knowledge Management (pp. 174–189). Springer
Nature Switzerland. https://doi.org/10.1007/978-3-031-77792-9_11'
bibtex: '@inproceedings{Vollmers_Srivastava_Zahera_Moussallem_Ngonga Ngomo_2025,
place={Cham}, title={UniQ-Gen: Unified Query Generation Across Multiple Knowledge
Graphs}, DOI={https://doi.org/10.1007/978-3-031-77792-9_11},
booktitle={Knowledge Engineering and Knowledge Management}, publisher={Springer
Nature Switzerland}, author={Vollmers, Daniel and Srivastava, Nikit and Zahera,
Hamada Mohamed Abdelsamee and Moussallem, Diego and Ngonga Ngomo, Axel-Cyrille},
editor={Alam, Mehwish and Rospocher, Marco and van Erp, Marieke and Hollink, Laura
and Gesese, Genet Asefa}, year={2025}, pages={174–189} }'
chicago: 'Vollmers, Daniel, Nikit Srivastava, Hamada Mohamed Abdelsamee Zahera,
Diego Moussallem, and Axel-Cyrille Ngonga Ngomo. “UniQ-Gen: Unified Query Generation
Across Multiple Knowledge Graphs.” In Knowledge Engineering and Knowledge Management,
edited by Mehwish Alam, Marco Rospocher, Marieke van Erp, Laura Hollink, and Genet
Asefa Gesese, 174–189. Cham: Springer Nature Switzerland, 2025. https://doi.org/10.1007/978-3-031-77792-9_11.'
ieee: 'D. Vollmers, N. Srivastava, H. M. A. Zahera, D. Moussallem, and A.-C. Ngonga
Ngomo, “UniQ-Gen: Unified Query Generation Across Multiple Knowledge Graphs,”
in Knowledge Engineering and Knowledge Management, 2025, pp. 174–189, doi:
https://doi.org/10.1007/978-3-031-77792-9_11.'
mla: 'Vollmers, Daniel, et al. “UniQ-Gen: Unified Query Generation Across Multiple
Knowledge Graphs.” Knowledge Engineering and Knowledge Management, edited
by Mehwish Alam et al., Springer Nature Switzerland, 2025, pp. 174–189, doi:https://doi.org/10.1007/978-3-031-77792-9_11.'
short: 'D. Vollmers, N. Srivastava, H.M.A. Zahera, D. Moussallem, A.-C. Ngonga Ngomo,
in: M. Alam, M. Rospocher, M. van Erp, L. Hollink, G.A. Gesese (Eds.), Knowledge
Engineering and Knowledge Management, Springer Nature Switzerland, Cham, 2025,
pp. 174–189.'
date_created: 2024-11-22T12:56:54Z
date_updated: 2024-11-22T12:58:59Z
doi: https://doi.org/10.1007/978-3-031-77792-9_11
editor:
- first_name: Mehwish
full_name: Alam, Mehwish
last_name: Alam
- first_name: Marco
full_name: Rospocher, Marco
last_name: Rospocher
- first_name: Marieke
full_name: van Erp, Marieke
last_name: van Erp
- first_name: Laura
full_name: Hollink, Laura
last_name: Hollink
- first_name: Genet Asefa
full_name: Gesese, Genet Asefa
last_name: Gesese
language:
- iso: eng
page: 174–189
place: Cham
publication: Knowledge Engineering and Knowledge Management
publication_identifier:
isbn:
- 978-3-031-77792-9
publisher: Springer Nature Switzerland
status: public
title: 'UniQ-Gen: Unified Query Generation Across Multiple Knowledge Graphs'
type: conference
user_id: '70066'
year: '2025'
...
---
_id: '60718'
abstract:
- lang: eng
text: "The ability to generate explanations that are understood by explainees is
the\r\nquintessence of explainable artificial intelligence. Since understanding\r\ndepends
on the explainee's background and needs, recent research focused on\r\nco-constructive
explanation dialogues, where an explainer continuously monitors\r\nthe explainee's
understanding and adapts their explanations dynamically. We\r\ninvestigate the
ability of large language models (LLMs) to engage as explainers\r\nin co-constructive
explanation dialogues. In particular, we present a user\r\nstudy in which explainees
interact with an LLM in two settings, one of which\r\ninvolves the LLM being instructed
to explain a topic co-constructively. We\r\nevaluate the explainees' understanding
before and after the dialogue, as well\r\nas their perception of the LLMs' co-constructive
behavior. Our results suggest\r\nthat LLMs show some co-constructive behaviors,
such as asking verification\r\nquestions, that foster the explainees' engagement
and can improve understanding\r\nof a topic. However, their ability to effectively
monitor the current\r\nunderstanding and scaffold the explanations accordingly
remains limited."
author:
- first_name: Leandra
full_name: Fichtel, Leandra
last_name: Fichtel
- first_name: Maximilian
full_name: Spliethöver, Maximilian
last_name: Spliethöver
- first_name: Eyke
full_name: Hüllermeier, Eyke
last_name: Hüllermeier
- first_name: Patricia
full_name: Jimenez, Patricia
id: '103339'
last_name: Jimenez
- first_name: Nils
full_name: Klowait, Nils
id: '98454'
last_name: Klowait
orcid: 0000-0002-7347-099X
- first_name: Stefan
full_name: Kopp, Stefan
last_name: Kopp
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: Amelie
full_name: Robrecht, Amelie
last_name: Robrecht
- first_name: Ingrid
full_name: Scharlau, Ingrid
id: '451'
last_name: Scharlau
orcid: 0000-0003-2364-9489
- first_name: Lutz
full_name: Terfloth, Lutz
id: '37320'
last_name: Terfloth
- first_name: Anna-Lisa
full_name: Vollmer, Anna-Lisa
last_name: Vollmer
- first_name: Henning
full_name: Wachsmuth, Henning
last_name: Wachsmuth
citation:
ama: Fichtel L, Spliethöver M, Hüllermeier E, et al. Investigating Co-Constructive
Behavior of Large Language Models in Explanation Dialogues. arXiv:250418483.
Published online 2025.
apa: Fichtel, L., Spliethöver, M., Hüllermeier, E., Jimenez, P., Klowait, N., Kopp,
S., Ngonga Ngomo, A.-C., Robrecht, A., Scharlau, I., Terfloth, L., Vollmer, A.-L.,
& Wachsmuth, H. (2025). Investigating Co-Constructive Behavior of Large Language
Models in Explanation Dialogues. In arXiv:2504.18483.
bibtex: '@article{Fichtel_Spliethöver_Hüllermeier_Jimenez_Klowait_Kopp_Ngonga Ngomo_Robrecht_Scharlau_Terfloth_et
al._2025, title={Investigating Co-Constructive Behavior of Large Language Models
in Explanation Dialogues}, journal={arXiv:2504.18483}, author={Fichtel, Leandra
and Spliethöver, Maximilian and Hüllermeier, Eyke and Jimenez, Patricia and Klowait,
Nils and Kopp, Stefan and Ngonga Ngomo, Axel-Cyrille and Robrecht, Amelie and
Scharlau, Ingrid and Terfloth, Lutz and et al.}, year={2025} }'
chicago: Fichtel, Leandra, Maximilian Spliethöver, Eyke Hüllermeier, Patricia Jimenez,
Nils Klowait, Stefan Kopp, Axel-Cyrille Ngonga Ngomo, et al. “Investigating Co-Constructive
Behavior of Large Language Models in Explanation Dialogues.” ArXiv:2504.18483,
2025.
ieee: L. Fichtel et al., “Investigating Co-Constructive Behavior of Large
Language Models in Explanation Dialogues,” arXiv:2504.18483. 2025.
mla: Fichtel, Leandra, et al. “Investigating Co-Constructive Behavior of Large Language
Models in Explanation Dialogues.” ArXiv:2504.18483, 2025.
short: L. Fichtel, M. Spliethöver, E. Hüllermeier, P. Jimenez, N. Klowait, S. Kopp,
A.-C. Ngonga Ngomo, A. Robrecht, I. Scharlau, L. Terfloth, A.-L. Vollmer, H. Wachsmuth,
ArXiv:2504.18483 (2025).
date_created: 2025-07-22T13:10:42Z
date_updated: 2025-07-23T11:23:32Z
external_id:
arxiv:
- '2504.18483'
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- url: https://arxiv.org/pdf/2504.18483
page: '20'
project:
- _id: '121'
grant_number: '438445824'
name: 'TRR 318 - B01: TRR 318 - Ein dialogbasierter Ansatz zur Erklärung von Modellen
des maschinellen Lernens (Teilprojekt B01)'
- _id: '127'
name: 'TRR 318 - C4: TRR 318 - Subproject C4 - Metaphern als Werkzeug des Erklärens'
- _id: '122'
name: 'TRR 318 - B3: TRR 318 - Subproject B3'
- _id: '119'
name: 'TRR 318 - Ö: TRR 318 - Project Area Ö'
- _id: '114'
grant_number: '438445824'
name: 'TRR 318 - A04: TRR 318 - Integration des technischen Modells in das Partnermodell
bei der Erklärung von digitalen Artefakten (Teilprojekt A04)'
publication: arXiv:2504.18483
status: public
title: Investigating Co-Constructive Behavior of Large Language Models in Explanation
Dialogues
type: preprint
user_id: '98454'
year: '2025'
...
---
_id: '61123'
abstract:
- lang: eng
text: Knowledge graphs are used by a growing number of applications to represent
structured data. Hence, evaluating the veracity of assertions in knowledge graphs—dubbed
fact checking—is currently a challenge of growing importance. However, manual
fact checking is commonly impractical due to the sheer size of knowledge graphs.
This paper is a systematic survey of recent works on automatic fact checking with
a focus on knowledge graphs. We present recent fact-checking approaches, the varied
sources they use as background knowledge, and the features they rely upon. Finally,
we draw conclusions pertaining to possible future research directions in fact
checking knowledge graphs.
article_number: '3749838'
article_type: original
author:
- first_name: Umair
full_name: Qudus, Umair
id: '83392'
last_name: Qudus
orcid: 0000-0001-6714-8729
- first_name: Michael
full_name: Röder, Michael
id: '67199'
last_name: Röder
orcid: https://orcid.org/0000-0002-8609-8277
- first_name: Muhammad
full_name: Saleem, Muhammad
last_name: Saleem
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: Qudus U, Röder M, Saleem M, Ngonga Ngomo A-C. Fact Checking Knowledge Graphs
-- A Survey. ACM Computing Surveys. 2025;58. doi:10.1145/3749838
apa: Qudus, U., Röder, M., Saleem, M., & Ngonga Ngomo, A.-C. (2025). Fact Checking
Knowledge Graphs -- A Survey. ACM Computing Surveys, 58, Article
3749838. https://doi.org/10.1145/3749838
bibtex: '@article{Qudus_Röder_Saleem_Ngonga Ngomo_2025, title={Fact Checking Knowledge
Graphs -- A Survey}, volume={58}, DOI={10.1145/3749838},
number={3749838}, journal={ACM Computing Surveys}, publisher={Association for
Computing Machinery (ACM)}, author={Qudus, Umair and Röder, Michael and Saleem,
Muhammad and Ngonga Ngomo, Axel-Cyrille}, year={2025} }'
chicago: Qudus, Umair, Michael Röder, Muhammad Saleem, and Axel-Cyrille Ngonga Ngomo.
“Fact Checking Knowledge Graphs -- A Survey.” ACM Computing Surveys 58
(2025). https://doi.org/10.1145/3749838.
ieee: 'U. Qudus, M. Röder, M. Saleem, and A.-C. Ngonga Ngomo, “Fact Checking Knowledge
Graphs -- A Survey,” ACM Computing Surveys, vol. 58, Art. no. 3749838,
2025, doi: 10.1145/3749838.'
mla: Qudus, Umair, et al. “Fact Checking Knowledge Graphs -- A Survey.” ACM Computing
Surveys, vol. 58, 3749838, Association for Computing Machinery (ACM), 2025,
doi:10.1145/3749838.
short: U. Qudus, M. Röder, M. Saleem, A.-C. Ngonga Ngomo, ACM Computing Surveys
58 (2025).
date_created: 2025-09-03T15:46:43Z
date_updated: 2025-09-11T09:30:28Z
ddc:
- '006'
department:
- _id: '574'
doi: 10.1145/3749838
external_id:
unknown:
- 10.1145/3749838
file:
- access_level: closed
content_type: application/pdf
creator: uqudus
date_created: 2025-09-11T09:26:29Z
date_updated: 2025-09-11T09:26:29Z
file_id: '61195'
file_name: 3749838.pdf
file_size: 1062387
relation: main_file
success: 1
file_date_updated: 2025-09-11T09:26:29Z
has_accepted_license: '1'
intvolume: ' 58'
keyword:
- fact checking
- knowledge graphs
- fact-checkers
- check worthiness
- evidence retrieval
- trust
- veracity.
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://dl.acm.org/doi/pdf/10.1145/3749838
oa: '1'
popular_science: '1'
publication: ACM Computing Surveys
publication_identifier:
issn:
- 0360-0300
- 1557-7341
publication_status: published
publisher: Association for Computing Machinery (ACM)
quality_controlled: '1'
status: public
title: Fact Checking Knowledge Graphs -- A Survey
type: journal_article
user_id: '83392'
volume: 58
year: '2025'
...
---
_id: '59054'
author:
- first_name: Asep Fajar
full_name: Firmansyah, Asep Fajar
id: '76787'
last_name: Firmansyah
- first_name: Hamada Mohamed Abdelsamee
full_name: Zahera, Hamada Mohamed Abdelsamee
id: '72768'
last_name: Zahera
orcid: 0000-0003-0215-1278
- first_name: Mohamed
full_name: Sherif, Mohamed
id: '67234'
last_name: Sherif
orcid: https://orcid.org/0000-0002-9927-2203
- first_name: Diego
full_name: Moussallem, Diego
id: '71635'
last_name: Moussallem
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Firmansyah AF, Zahera HMA, Sherif M, Moussallem D, Ngonga Ngomo A-C. ANTS:
Abstractive Entity Summarization in Knowledge Graphs. In: ESWC2025. The
Semantic Web. pringer Nature Switzerland; 2025:133--151. doi:10.1007/978-3-031-94575-5_8'
apa: 'Firmansyah, A. F., Zahera, H. M. A., Sherif, M., Moussallem, D., & Ngonga
Ngomo, A.-C. (2025). ANTS: Abstractive Entity Summarization in Knowledge Graphs.
ESWC2025, 133--151. https://doi.org/10.1007/978-3-031-94575-5_8'
bibtex: '@inproceedings{Firmansyah_Zahera_Sherif_Moussallem_Ngonga Ngomo_2025, series={The
Semantic Web}, title={ANTS: Abstractive Entity Summarization in Knowledge Graphs},
DOI={10.1007/978-3-031-94575-5_8},
booktitle={ESWC2025}, publisher={pringer Nature Switzerland}, author={Firmansyah,
Asep Fajar and Zahera, Hamada Mohamed Abdelsamee and Sherif, Mohamed and Moussallem,
Diego and Ngonga Ngomo, Axel-Cyrille}, year={2025}, pages={133--151}, collection={The
Semantic Web} }'
chicago: 'Firmansyah, Asep Fajar, Hamada Mohamed Abdelsamee Zahera, Mohamed Sherif,
Diego Moussallem, and Axel-Cyrille Ngonga Ngomo. “ANTS: Abstractive Entity Summarization
in Knowledge Graphs.” In ESWC2025, 133--151. The Semantic Web. pringer
Nature Switzerland, 2025. https://doi.org/10.1007/978-3-031-94575-5_8.'
ieee: 'A. F. Firmansyah, H. M. A. Zahera, M. Sherif, D. Moussallem, and A.-C. Ngonga
Ngomo, “ANTS: Abstractive Entity Summarization in Knowledge Graphs,” in ESWC2025,
2025, pp. 133--151, doi: 10.1007/978-3-031-94575-5_8.'
mla: 'Firmansyah, Asep Fajar, et al. “ANTS: Abstractive Entity Summarization in
Knowledge Graphs.” ESWC2025, pringer Nature Switzerland, 2025, pp. 133--151,
doi:10.1007/978-3-031-94575-5_8.'
short: 'A.F. Firmansyah, H.M.A. Zahera, M. Sherif, D. Moussallem, A.-C. Ngonga Ngomo,
in: ESWC2025, pringer Nature Switzerland, 2025, pp. 133--151.'
conference:
name: ESWC 2025
date_created: 2025-03-17T13:41:48Z
date_updated: 2025-09-11T10:00:44Z
department:
- _id: '574'
doi: 10.1007/978-3-031-94575-5_8
keyword:
- firmansyah mousallem ngonga sherif zahera
language:
- iso: eng
page: 133--151
publication: ESWC2025
publication_identifier:
isbn:
- 978-3-031-94575-5
publication_status: published
publisher: pringer Nature Switzerland
series_title: The Semantic Web
status: public
title: 'ANTS: Abstractive Entity Summarization in Knowledge Graphs'
type: conference
user_id: '67234'
year: '2025'
...
---
_id: '61202'
abstract:
- lang: eng
text: The number of datasets on the web of data increases continuously. However,
the knowledge contained therein cannot be fully utilized without finding links
between the entities contained in these datasets. Equivalent entities can not
be identified solely by checking the equivalence of IRIs because of the different
origins and naming schemes of different data providers. Yet, such equivalences
can be discovered by computing the similarity of their attributes. In this paper
we propose GLIDE, an approach that links entities from two different datasets
by embedding a joint model of these datasets enriched by additional relations
describing the similarity of literals. The joint model is embedded into a latent
vector space while paying attention to juxtaposing similar literals. We evaluate
our approach against state-of-the-art algorithms using real-world datasets commonly
used in link discovery literature. The results show that GLIDE outperforms all
baselines on 5 of 7 datasets with perfect or near-perfect accuracy. Our approach
achieves its best performance on datasets that feature several literals with similarities.
Our experiments indicate that researchers should not only pay attention to equal
literals in knowledge graph embedding but should also be aware of the distance
between similar literals.
author:
- first_name: Alexander
full_name: Becker, Alexander
last_name: Becker
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: 'Mohamed '
full_name: 'Sherif, Mohamed '
last_name: Sherif
citation:
ama: 'Becker A, Ngonga Ngomo A-C, Sherif M. GLIDE: Knowledge Graph Linking using
Distance-Aware Embeddings. In: The Semantic Web – ISWC 2025. ; 2025.'
apa: 'Becker, A., Ngonga Ngomo, A.-C., & Sherif, M. (2025). GLIDE: Knowledge
Graph Linking using Distance-Aware Embeddings. The Semantic Web – ISWC 2025.
ISWC 2025.'
bibtex: '@inproceedings{Becker_Ngonga Ngomo_Sherif_2025, place={Nara, Japan}, title={GLIDE:
Knowledge Graph Linking using Distance-Aware Embeddings}, booktitle={The Semantic
Web – ISWC 2025}, author={Becker, Alexander and Ngonga Ngomo, Axel-Cyrille and
Sherif, Mohamed }, year={2025} }'
chicago: 'Becker, Alexander, Axel-Cyrille Ngonga Ngomo, and Mohamed Sherif. “GLIDE:
Knowledge Graph Linking Using Distance-Aware Embeddings.” In The Semantic Web
– ISWC 2025. Nara, Japan, 2025.'
ieee: 'A. Becker, A.-C. Ngonga Ngomo, and M. Sherif, “GLIDE: Knowledge Graph Linking
using Distance-Aware Embeddings,” presented at the ISWC 2025, 2025.'
mla: 'Becker, Alexander, et al. “GLIDE: Knowledge Graph Linking Using Distance-Aware
Embeddings.” The Semantic Web – ISWC 2025, 2025.'
short: 'A. Becker, A.-C. Ngonga Ngomo, M. Sherif, in: The Semantic Web – ISWC 2025,
Nara, Japan, 2025.'
conference:
name: ISWC 2025
date_created: 2025-09-11T10:04:16Z
date_updated: 2025-09-11T10:34:52Z
department:
- _id: '574'
keyword:
- becker sherif enexa sailproject dice simba ngonga whale
language:
- iso: eng
place: Nara, Japan
publication: The Semantic Web – ISWC 2025
status: public
title: 'GLIDE: Knowledge Graph Linking using Distance-Aware Embeddings'
type: conference
user_id: '67234'
year: '2025'
...
---
_id: '61134'
author:
- first_name: Ali
full_name: Manzoor, Ali
id: '77309'
last_name: Manzoor
orcid: https://orcid.org/0000-0001-8403-5160
- first_name: René
full_name: Speck, René
id: '70843'
last_name: Speck
- first_name: Hamada Mohamed Abdelsamee
full_name: Zahera, Hamada Mohamed Abdelsamee
id: '72768'
last_name: Zahera
orcid: 0000-0003-0215-1278
- first_name: Muhammad
full_name: Saleem, Muhammad
last_name: Saleem
- first_name: Diego
full_name: Moussallem, Diego
id: '71635'
last_name: Moussallem
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: Manzoor A, Speck R, Zahera HMA, Saleem M, Moussallem D, Ngonga Ngomo A-C. Multilingual
Relation Extraction - A Survey. IEEE Access. Published online 2025:1-1.
doi:10.1109/access.2025.3604258
apa: Manzoor, A., Speck, R., Zahera, H. M. A., Saleem, M., Moussallem, D., &
Ngonga Ngomo, A.-C. (2025). Multilingual Relation Extraction - A Survey. IEEE
Access, 1–1. https://doi.org/10.1109/access.2025.3604258
bibtex: '@article{Manzoor_Speck_Zahera_Saleem_Moussallem_Ngonga Ngomo_2025, title={Multilingual
Relation Extraction - A Survey}, DOI={10.1109/access.2025.3604258},
journal={IEEE Access}, publisher={Institute of Electrical and Electronics Engineers
(IEEE)}, author={Manzoor, Ali and Speck, René and Zahera, Hamada Mohamed Abdelsamee
and Saleem, Muhammad and Moussallem, Diego and Ngonga Ngomo, Axel-Cyrille}, year={2025},
pages={1–1} }'
chicago: Manzoor, Ali, René Speck, Hamada Mohamed Abdelsamee Zahera, Muhammad Saleem,
Diego Moussallem, and Axel-Cyrille Ngonga Ngomo. “Multilingual Relation Extraction
- A Survey.” IEEE Access, 2025, 1–1. https://doi.org/10.1109/access.2025.3604258.
ieee: 'A. Manzoor, R. Speck, H. M. A. Zahera, M. Saleem, D. Moussallem, and A.-C.
Ngonga Ngomo, “Multilingual Relation Extraction - A Survey,” IEEE Access,
pp. 1–1, 2025, doi: 10.1109/access.2025.3604258.'
mla: Manzoor, Ali, et al. “Multilingual Relation Extraction - A Survey.” IEEE
Access, Institute of Electrical and Electronics Engineers (IEEE), 2025, pp.
1–1, doi:10.1109/access.2025.3604258.
short: A. Manzoor, R. Speck, H.M.A. Zahera, M. Saleem, D. Moussallem, A.-C. Ngonga
Ngomo, IEEE Access (2025) 1–1.
date_created: 2025-09-04T13:32:08Z
date_updated: 2025-09-11T11:14:27Z
department:
- _id: '574'
doi: 10.1109/access.2025.3604258
language:
- iso: eng
page: 1-1
publication: IEEE Access
publication_identifier:
issn:
- 2169-3536
publication_status: published
publisher: Institute of Electrical and Electronics Engineers (IEEE)
status: public
title: Multilingual Relation Extraction - A Survey
type: journal_article
user_id: '77309'
year: '2025'
...
---
_id: '61234'
abstract:
- lang: eng
text: "The ability to generate explanations that are understood by explainees is
the\r\nquintessence of explainable artificial intelligence. Since understanding\r\ndepends
on the explainee's background and needs, recent research focused on\r\nco-constructive
explanation dialogues, where an explainer continuously monitors\r\nthe explainee's
understanding and adapts their explanations dynamically. We\r\ninvestigate the
ability of large language models (LLMs) to engage as explainers\r\nin co-constructive
explanation dialogues. In particular, we present a user\r\nstudy in which explainees
interact with an LLM in two settings, one of which\r\ninvolves the LLM being instructed
to explain a topic co-constructively. We\r\nevaluate the explainees' understanding
before and after the dialogue, as well\r\nas their perception of the LLMs' co-constructive
behavior. Our results suggest\r\nthat LLMs show some co-constructive behaviors,
such as asking verification\r\nquestions, that foster the explainees' engagement
and can improve understanding\r\nof a topic. However, their ability to effectively
monitor the current\r\nunderstanding and scaffold the explanations accordingly
remains limited."
author:
- first_name: Leandra
full_name: Fichtel, Leandra
last_name: Fichtel
- first_name: Maximilian
full_name: Spliethöver, Maximilian
id: '84035'
last_name: Spliethöver
orcid: 0000-0003-4364-1409
- first_name: Eyke
full_name: Hüllermeier, Eyke
id: '48129'
last_name: Hüllermeier
- first_name: Patricia
full_name: Jimenez, Patricia
id: '103339'
last_name: Jimenez
- first_name: Nils
full_name: Klowait, Nils
id: '98454'
last_name: Klowait
orcid: 0000-0002-7347-099X
- first_name: Stefan
full_name: Kopp, Stefan
last_name: Kopp
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: Amelie
full_name: Robrecht, Amelie
id: '91982'
last_name: Robrecht
orcid: 0000-0001-5622-8248
- first_name: Ingrid
full_name: Scharlau, Ingrid
id: '451'
last_name: Scharlau
orcid: 0000-0003-2364-9489
- first_name: Lutz
full_name: Terfloth, Lutz
id: '37320'
last_name: Terfloth
- first_name: Anna-Lisa
full_name: Vollmer, Anna-Lisa
id: '86589'
last_name: Vollmer
- first_name: Henning
full_name: Wachsmuth, Henning
id: '3900'
last_name: Wachsmuth
citation:
ama: 'Fichtel L, Spliethöver M, Hüllermeier E, et al. Investigating Co-Constructive
Behavior of Large Language Models in Explanation Dialogues. In: Proceedings
of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue.
Association for Computational Linguistics.'
apa: Fichtel, L., Spliethöver, M., Hüllermeier, E., Jimenez, P., Klowait, N., Kopp,
S., Ngonga Ngomo, A.-C., Robrecht, A., Scharlau, I., Terfloth, L., Vollmer, A.-L.,
& Wachsmuth, H. (n.d.). Investigating Co-Constructive Behavior of Large Language
Models in Explanation Dialogues. Proceedings of the 26th Annual Meeting of
the Special Interest Group on Discourse and Dialogue. Annual Meeting of the
Special Interest Group on Discourse and Dialogue.
bibtex: '@inproceedings{Fichtel_Spliethöver_Hüllermeier_Jimenez_Klowait_Kopp_Ngonga
Ngomo_Robrecht_Scharlau_Terfloth_et al., place={Avignon, France}, title={Investigating
Co-Constructive Behavior of Large Language Models in Explanation Dialogues},
booktitle={Proceedings of the 26th Annual Meeting of the Special Interest Group
on Discourse and Dialogue}, publisher={Association for Computational Linguistics},
author={Fichtel, Leandra and Spliethöver, Maximilian and Hüllermeier, Eyke and
Jimenez, Patricia and Klowait, Nils and Kopp, Stefan and Ngonga Ngomo, Axel-Cyrille
and Robrecht, Amelie and Scharlau, Ingrid and Terfloth, Lutz and et al.} }'
chicago: 'Fichtel, Leandra, Maximilian Spliethöver, Eyke Hüllermeier, Patricia Jimenez,
Nils Klowait, Stefan Kopp, Axel-Cyrille Ngonga Ngomo, et al. “Investigating Co-Constructive
Behavior of Large Language Models in Explanation Dialogues.” In Proceedings
of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue.
Avignon, France: Association for Computational Linguistics, n.d.'
ieee: L. Fichtel et al., “Investigating Co-Constructive Behavior of Large
Language Models in Explanation Dialogues,” presented at the Annual Meeting of
the Special Interest Group on Discourse and Dialogue.
mla: Fichtel, Leandra, et al. “Investigating Co-Constructive Behavior of Large Language
Models in Explanation Dialogues.” Proceedings of the 26th Annual Meeting of
the Special Interest Group on Discourse and Dialogue, Association for Computational
Linguistics.
short: 'L. Fichtel, M. Spliethöver, E. Hüllermeier, P. Jimenez, N. Klowait, S. Kopp,
A.-C. Ngonga Ngomo, A. Robrecht, I. Scharlau, L. Terfloth, A.-L. Vollmer, H. Wachsmuth,
in: Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse
and Dialogue, Association for Computational Linguistics, Avignon, France, n.d.'
conference:
name: Annual Meeting of the Special Interest Group on Discourse and Dialogue
date_created: 2025-09-11T16:11:17Z
date_updated: 2025-09-12T09:50:48Z
department:
- _id: '660'
external_id:
arxiv:
- '2504.18483'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2504.18483
oa: '1'
place: Avignon, France
project:
- _id: '118'
name: 'TRR 318: Project Area INF'
- _id: '121'
name: 'TRR 318; TP B01: Ein dialogbasierter Ansatz zur Erklärung von Modellen des
maschinellen Lernens'
- _id: '127'
name: 'TRR 318; TP C04: Metaphern als Werkzeug des Erklärens'
- _id: '122'
name: TRR 318 - Subproject B3
- _id: '119'
name: TRR 318 - Project Area Ö
- _id: '114'
name: 'TRR 318; TP A04: Integration des technischen Modells in das Partnermodell
bei der Erklärung von digitalen Artefakten'
publication: Proceedings of the 26th Annual Meeting of the Special Interest Group
on Discourse and Dialogue
publication_status: accepted
publisher: Association for Computational Linguistics
related_material:
link:
- relation: software
url: https://github.com/webis-de/sigdial25-co-constructive-llms
- relation: research_data
url: https://github.com/webis-de/sigdial25-co-constructive-llms-data
status: public
title: Investigating Co-Constructive Behavior of Large Language Models in Explanation
Dialogues
type: conference
user_id: '84035'
year: '2025'
...
---
_id: '61819'
author:
- first_name: Jörg
full_name: Papenkordt, Jörg
id: '44648'
last_name: Papenkordt
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: Kirsten
full_name: Thommes, Kirsten
id: '72497'
last_name: Thommes
citation:
ama: Papenkordt J, Ngonga Ngomo A-C, Thommes K. Are numerical or verbal explanations
of AI the key to appropriate user reliance and error detection? Behaviour &
Information Technology. Published online 2025:1-22. doi:10.1080/0144929x.2025.2568928
apa: Papenkordt, J., Ngonga Ngomo, A.-C., & Thommes, K. (2025). Are numerical
or verbal explanations of AI the key to appropriate user reliance and error detection?
Behaviour & Information Technology, 1–22. https://doi.org/10.1080/0144929x.2025.2568928
bibtex: '@article{Papenkordt_Ngonga Ngomo_Thommes_2025, title={Are numerical or
verbal explanations of AI the key to appropriate user reliance and error detection?},
DOI={10.1080/0144929x.2025.2568928},
journal={Behaviour & Information Technology}, publisher={Informa UK Limited},
author={Papenkordt, Jörg and Ngonga Ngomo, Axel-Cyrille and Thommes, Kirsten},
year={2025}, pages={1–22} }'
chicago: Papenkordt, Jörg, Axel-Cyrille Ngonga Ngomo, and Kirsten Thommes. “Are
Numerical or Verbal Explanations of AI the Key to Appropriate User Reliance and
Error Detection?” Behaviour & Information Technology, 2025, 1–22.
https://doi.org/10.1080/0144929x.2025.2568928.
ieee: 'J. Papenkordt, A.-C. Ngonga Ngomo, and K. Thommes, “Are numerical or verbal
explanations of AI the key to appropriate user reliance and error detection?,”
Behaviour & Information Technology, pp. 1–22, 2025, doi: 10.1080/0144929x.2025.2568928.'
mla: Papenkordt, Jörg, et al. “Are Numerical or Verbal Explanations of AI the Key
to Appropriate User Reliance and Error Detection?” Behaviour & Information
Technology, Informa UK Limited, 2025, pp. 1–22, doi:10.1080/0144929x.2025.2568928.
short: J. Papenkordt, A.-C. Ngonga Ngomo, K. Thommes, Behaviour & Information
Technology (2025) 1–22.
date_created: 2025-10-13T13:33:14Z
date_updated: 2025-10-14T06:12:07Z
department:
- _id: '178'
- _id: '184'
doi: 10.1080/0144929x.2025.2568928
language:
- iso: eng
page: 1-22
project:
- _id: '113'
name: TRR 318 - Subproject A3
- _id: '810'
name: arbeitswelt + - KI für die Arbeitswelt des industriellen Mittelstands
publication: Behaviour & Information Technology
publication_identifier:
issn:
- 0144-929X
- 1362-3001
publication_status: published
publisher: Informa UK Limited
status: public
title: Are numerical or verbal explanations of AI the key to appropriate user reliance
and error detection?
type: journal_article
user_id: '72497'
year: '2025'
...
---
_id: '62119'
author:
- first_name: Reda
full_name: Ihtassine, Reda
id: '103911'
last_name: Ihtassine
- first_name: Asep Fajar
full_name: Firmansyah, Asep Fajar
id: '76787'
last_name: Firmansyah
- first_name: Nikit
full_name: Srivastava, Nikit
id: '70066'
last_name: Srivastava
orcid: 0009-0004-5164-4911
- first_name: Manzoor
full_name: Ali, Manzoor
last_name: Ali
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: Mohamed
full_name: Sherif, Mohamed
id: '67234'
last_name: Sherif
orcid: https://orcid.org/0000-0002-9927-2203
citation:
ama: 'Ihtassine R, Firmansyah AF, Srivastava N, Ali M, Ngonga Ngomo A-C, Sherif
M. NL2LS: LLM-based Automatic Linking of Knowledge Graphs. In: Proceedings
of the 12th Knowledge Capture Conference 2025, {K-CAP} 2025, The Thirteenth International
Conference on Knowledge Capture, December 10 - 12, 2025, Dayton, Ohio, USA.
ACM; 2025.'
apa: 'Ihtassine, R., Firmansyah, A. F., Srivastava, N., Ali, M., Ngonga Ngomo, A.-C.,
& Sherif, M. (2025). NL2LS: LLM-based Automatic Linking of Knowledge Graphs.
Proceedings of the 12th Knowledge Capture Conference 2025, {K-CAP} 2025, The
Thirteenth International Conference on Knowledge Capture, December 10 - 12, 2025,
Dayton, Ohio, USA.'
bibtex: '@inproceedings{Ihtassine_Firmansyah_Srivastava_Ali_Ngonga Ngomo_Sherif_2025,
title={NL2LS: LLM-based Automatic Linking of Knowledge Graphs}, booktitle={Proceedings
of the 12th Knowledge Capture Conference 2025, {K-CAP} 2025, The Thirteenth International
Conference on Knowledge Capture, December 10 - 12, 2025, Dayton, Ohio, USA}, publisher={ACM},
author={Ihtassine, Reda and Firmansyah, Asep Fajar and Srivastava, Nikit and Ali,
Manzoor and Ngonga Ngomo, Axel-Cyrille and Sherif, Mohamed}, year={2025} }'
chicago: 'Ihtassine, Reda, Asep Fajar Firmansyah, Nikit Srivastava, Manzoor Ali,
Axel-Cyrille Ngonga Ngomo, and Mohamed Sherif. “NL2LS: LLM-Based Automatic Linking
of Knowledge Graphs.” In Proceedings of the 12th Knowledge Capture Conference
2025, {K-CAP} 2025, The Thirteenth International Conference on Knowledge Capture,
December 10 - 12, 2025, Dayton, Ohio, USA. ACM, 2025.'
ieee: 'R. Ihtassine, A. F. Firmansyah, N. Srivastava, M. Ali, A.-C. Ngonga Ngomo,
and M. Sherif, “NL2LS: LLM-based Automatic Linking of Knowledge Graphs,” 2025.'
mla: 'Ihtassine, Reda, et al. “NL2LS: LLM-Based Automatic Linking of Knowledge Graphs.”
Proceedings of the 12th Knowledge Capture Conference 2025, {K-CAP} 2025, The
Thirteenth International Conference on Knowledge Capture, December 10 - 12, 2025,
Dayton, Ohio, USA, ACM, 2025.'
short: 'R. Ihtassine, A.F. Firmansyah, N. Srivastava, M. Ali, A.-C. Ngonga Ngomo,
M. Sherif, in: Proceedings of the 12th Knowledge Capture Conference 2025, {K-CAP}
2025, The Thirteenth International Conference on Knowledge Capture, December 10
- 12, 2025, Dayton, Ohio, USA, ACM, 2025.'
date_created: 2025-11-06T15:13:39Z
date_updated: 2025-11-06T15:19:28Z
department:
- _id: '574'
keyword:
- Srivastava ali dice enexa firmansyah ihtassine ngonga sailproject sherif whale
language:
- iso: eng
publication: Proceedings of the 12th Knowledge Capture Conference 2025, {K-CAP} 2025,
The Thirteenth International Conference on Knowledge Capture, December 10 - 12,
2025, Dayton, Ohio, USA
publisher: ACM
status: public
title: 'NL2LS: LLM-based Automatic Linking of Knowledge Graphs'
type: conference
user_id: '76787'
year: '2025'
...
---
_id: '61041'
abstract:
- lang: eng
text: Large Language Models (LLMs) are increasingly deployed in real-world applications
that require access to up-to-date knowledge. However, retraining LLMs is computationally
expensive. Therefore, knowledge editing techniques are crucial for maintaining
current information and correcting erroneous assertions within pre-trained models.
Current benchmarks for knowledge editing primarily focus on recalling edited facts,
often neglecting their logical consequences. To address this limitation, we introduce
a new benchmark designed to evaluate how knowledge editing methods handle the
logical consequences of a single fact edit. Our benchmark extracts relevant logical
rules from a knowledge graph for a given edit. Then, it generates multi-hop questions
based on these rules to assess the impact on logical consequences. Our findings
indicate that while existing knowledge editing approaches can accurately insert
direct assertions into LLMs, they frequently fail to inject entailed knowledge.
Specifically, experiments with popular methods like ROME and FT reveal a substantial
performance gap, up to 24%, between evaluations on directly edited knowledge and
on entailed knowledge. This highlights the critical need for semantics-aware evaluation
frameworks in knowledge editing.
author:
- first_name: Tatiana
full_name: Moteu Ngoli, Tatiana
id: '99174'
last_name: Moteu Ngoli
- first_name: N'Dah Jean
full_name: Kouagou, N'Dah Jean
id: '87189'
last_name: Kouagou
- first_name: Hamada Mohamed Abdelsamee
full_name: Zahera, Hamada Mohamed Abdelsamee
id: '72768'
last_name: Zahera
orcid: 0000-0003-0215-1278
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Moteu Ngoli T, Kouagou NJ, Zahera HMA, Ngonga Ngomo A-C. Benchmarking Knowledge
Editing using Logical Rules. In: Proceedings of the 24th International Semantic
Web Conference (ISWC 2025). Springer, Cham; 2025:pp 41-56. doi:https://doi.org/10.1007/978-3-032-09530-5_3'
apa: Moteu Ngoli, T., Kouagou, N. J., Zahera, H. M. A., & Ngonga Ngomo, A.-C.
(2025). Benchmarking Knowledge Editing using Logical Rules. Proceedings of
the 24th International Semantic Web Conference (ISWC 2025), pp 41-56. https://doi.org/10.1007/978-3-032-09530-5_3
bibtex: '@inproceedings{Moteu Ngoli_Kouagou_Zahera_Ngonga Ngomo_2025, title={Benchmarking
Knowledge Editing using Logical Rules}, DOI={https://doi.org/10.1007/978-3-032-09530-5_3},
booktitle={Proceedings of the 24th International Semantic Web Conference (ISWC
2025)}, publisher={Springer, Cham}, author={Moteu Ngoli, Tatiana and Kouagou,
N’Dah Jean and Zahera, Hamada Mohamed Abdelsamee and Ngonga Ngomo, Axel-Cyrille},
year={2025}, pages={pp 41-56} }'
chicago: Moteu Ngoli, Tatiana, N’Dah Jean Kouagou, Hamada Mohamed Abdelsamee Zahera,
and Axel-Cyrille Ngonga Ngomo. “Benchmarking Knowledge Editing Using Logical Rules.”
In Proceedings of the 24th International Semantic Web Conference (ISWC 2025),
pp 41-56. Springer, Cham, 2025. https://doi.org/10.1007/978-3-032-09530-5_3.
ieee: 'T. Moteu Ngoli, N. J. Kouagou, H. M. A. Zahera, and A.-C. Ngonga Ngomo, “Benchmarking
Knowledge Editing using Logical Rules,” in Proceedings of the 24th International
Semantic Web Conference (ISWC 2025), Nara, Japan, 2025, p. pp 41-56, doi:
https://doi.org/10.1007/978-3-032-09530-5_3.'
mla: Moteu Ngoli, Tatiana, et al. “Benchmarking Knowledge Editing Using Logical
Rules.” Proceedings of the 24th International Semantic Web Conference (ISWC
2025), Springer, Cham, 2025, p. pp 41-56, doi:https://doi.org/10.1007/978-3-032-09530-5_3.
short: 'T. Moteu Ngoli, N.J. Kouagou, H.M.A. Zahera, A.-C. Ngonga Ngomo, in: Proceedings
of the 24th International Semantic Web Conference (ISWC 2025), Springer, Cham,
2025, p. pp 41-56.'
conference:
end_date: 2025.11.6
location: Nara, Japan
name: The 24th International Semantic Web Conference (ISWC 2025)
start_date: 2025.11.2
date_created: 2025-08-27T13:17:55Z
date_updated: 2025-12-01T10:04:25Z
department:
- _id: '574'
doi: https://doi.org/10.1007/978-3-032-09530-5_3
keyword:
- dice sailproject moteu kouagou zahera ngonga
language:
- iso: eng
page: pp 41-56
project:
- _id: '285'
name: SAIL - Nachhaltiger Lebenszyklus von intelligenten soziotechnischen Systemen
publication: Proceedings of the 24th International Semantic Web Conference (ISWC 2025)
publication_identifier:
isbn:
- 978-3-032-09530-5
publication_status: published
publisher: Springer, Cham
status: public
title: Benchmarking Knowledge Editing using Logical Rules
type: conference
user_id: '99174'
year: '2025'
...
---
_id: '61753'
abstract:
- lang: eng
text: This paper presents LOLA, a massively multilingual large language model trained
on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture.
Our architectural and implementation choices address the challenge of harnessing
linguistic diversity while maintaining efficiency and avoiding the common pitfalls
of multilinguality. Our analysis of the evaluation results shows competitive performance
in natural language generation and understanding tasks. Additionally, we demonstrate
how the learned expert-routing mechanism exploits implicit phylogenetic linguistic
patterns to potentially alleviate the curse of multilinguality. We provide an
in-depth look at the training process, an analysis of the datasets, and a balanced
exploration of the model{’}s strengths and limitations. As an open-source model,
LOLA promotes reproducibility and serves as a robust foundation for future research.
Our findings enable the development of compute-efficient multilingual models with
strong, scalable performance across languages.
author:
- first_name: Nikit
full_name: Srivastava, Nikit
id: '70066'
last_name: Srivastava
orcid: 0009-0004-5164-4911
- first_name: Denis
full_name: Kuchelev, Denis
id: '70842'
last_name: Kuchelev
- first_name: Tatiana
full_name: Moteu Ngoli, Tatiana
id: '99174'
last_name: Moteu Ngoli
- first_name: Kshitij
full_name: Shetty, Kshitij
last_name: Shetty
- first_name: Michael
full_name: Röder, Michael
id: '67199'
last_name: Röder
orcid: https://orcid.org/0000-0002-8609-8277
- first_name: Hamada Mohamed Abdelsamee
full_name: Zahera, Hamada Mohamed Abdelsamee
id: '72768'
last_name: Zahera
orcid: 0000-0003-0215-1278
- first_name: Diego
full_name: Moussallem, Diego
id: '71635'
last_name: Moussallem
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Srivastava N, Kuchelev D, Moteu Ngoli T, et al. LOLA – An Open-Source Massively
Multilingual Large Language Model. In: Rambow O, Wanner L, Apidianaki M, Al-Khalifa
H, Eugenio BD, Schockaert S, eds. Proceedings of the 31st International Conference
on Computational Linguistics. Association for Computational Linguistics; 2025:6420–6446.'
apa: Srivastava, N., Kuchelev, D., Moteu Ngoli, T., Shetty, K., Röder, M., Zahera,
H. M. A., Moussallem, D., & Ngonga Ngomo, A.-C. (2025). LOLA – An Open-Source
Massively Multilingual Large Language Model. In O. Rambow, L. Wanner, M. Apidianaki,
H. Al-Khalifa, B. D. Eugenio, & S. Schockaert (Eds.), Proceedings of the
31st International Conference on Computational Linguistics (pp. 6420–6446).
Association for Computational Linguistics.
bibtex: '@inproceedings{Srivastava_Kuchelev_Moteu Ngoli_Shetty_Röder_Zahera_Moussallem_Ngonga
Ngomo_2025, place={Abu Dhabi, UAE}, title={LOLA – An Open-Source Massively Multilingual
Large Language Model}, booktitle={Proceedings of the 31st International Conference
on Computational Linguistics}, publisher={Association for Computational Linguistics},
author={Srivastava, Nikit and Kuchelev, Denis and Moteu Ngoli, Tatiana and Shetty,
Kshitij and Röder, Michael and Zahera, Hamada Mohamed Abdelsamee and Moussallem,
Diego and Ngonga Ngomo, Axel-Cyrille}, editor={Rambow, Owen and Wanner, Leo and
Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert,
Steven}, year={2025}, pages={6420–6446} }'
chicago: 'Srivastava, Nikit, Denis Kuchelev, Tatiana Moteu Ngoli, Kshitij Shetty,
Michael Röder, Hamada Mohamed Abdelsamee Zahera, Diego Moussallem, and Axel-Cyrille
Ngonga Ngomo. “LOLA – An Open-Source Massively Multilingual Large Language Model.”
In Proceedings of the 31st International Conference on Computational Linguistics,
edited by Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara
Di Eugenio, and Steven Schockaert, 6420–6446. Abu Dhabi, UAE: Association for
Computational Linguistics, 2025.'
ieee: N. Srivastava et al., “LOLA – An Open-Source Massively Multilingual
Large Language Model,” in Proceedings of the 31st International Conference
on Computational Linguistics, 2025, pp. 6420–6446.
mla: Srivastava, Nikit, et al. “LOLA – An Open-Source Massively Multilingual Large
Language Model.” Proceedings of the 31st International Conference on Computational
Linguistics, edited by Owen Rambow et al., Association for Computational Linguistics,
2025, pp. 6420–6446.
short: 'N. Srivastava, D. Kuchelev, T. Moteu Ngoli, K. Shetty, M. Röder, H.M.A.
Zahera, D. Moussallem, A.-C. Ngonga Ngomo, in: O. Rambow, L. Wanner, M. Apidianaki,
H. Al-Khalifa, B.D. Eugenio, S. Schockaert (Eds.), Proceedings of the 31st International
Conference on Computational Linguistics, Association for Computational Linguistics,
Abu Dhabi, UAE, 2025, pp. 6420–6446.'
date_created: 2025-10-08T11:02:30Z
date_updated: 2026-01-06T10:11:37Z
editor:
- first_name: Owen
full_name: Rambow, Owen
last_name: Rambow
- first_name: Leo
full_name: Wanner, Leo
last_name: Wanner
- first_name: Marianna
full_name: Apidianaki, Marianna
last_name: Apidianaki
- first_name: Hend
full_name: Al-Khalifa, Hend
last_name: Al-Khalifa
- first_name: Barbara Di
full_name: Eugenio, Barbara Di
last_name: Eugenio
- first_name: Steven
full_name: Schockaert, Steven
last_name: Schockaert
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://aclanthology.org/2025.coling-main.428.pdf
oa: '1'
page: 6420–6446
place: Abu Dhabi, UAE
publication: Proceedings of the 31st International Conference on Computational Linguistics
publisher: Association for Computational Linguistics
status: public
title: LOLA – An Open-Source Massively Multilingual Large Language Model
type: conference
user_id: '70066'
year: '2025'
...
---
_id: '63507'
author:
- first_name: Gaurav
full_name: Pandit, Gaurav
last_name: Pandit
- first_name: Michael
full_name: Röder, Michael
id: '67199'
last_name: Röder
orcid: https://orcid.org/0000-0002-8609-8277
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Pandit G, Röder M, Ngonga Ngomo A-C. Evaluating Approximate Nearest Neighbour
Search Systems on Knowledge Graph Embeddings. In: Lecture Notes in Computer
Science. Springer Nature Switzerland; 2025. doi:10.1007/978-3-031-94575-5_4'
apa: Pandit, G., Röder, M., & Ngonga Ngomo, A.-C. (2025). Evaluating Approximate
Nearest Neighbour Search Systems on Knowledge Graph Embeddings. In Lecture
Notes in Computer Science. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-94575-5_4
bibtex: '@inbook{Pandit_Röder_Ngonga Ngomo_2025, place={Cham}, title={Evaluating
Approximate Nearest Neighbour Search Systems on Knowledge Graph Embeddings}, DOI={10.1007/978-3-031-94575-5_4},
booktitle={Lecture Notes in Computer Science}, publisher={Springer Nature Switzerland},
author={Pandit, Gaurav and Röder, Michael and Ngonga Ngomo, Axel-Cyrille}, year={2025}
}'
chicago: 'Pandit, Gaurav, Michael Röder, and Axel-Cyrille Ngonga Ngomo. “Evaluating
Approximate Nearest Neighbour Search Systems on Knowledge Graph Embeddings.” In
Lecture Notes in Computer Science. Cham: Springer Nature Switzerland, 2025.
https://doi.org/10.1007/978-3-031-94575-5_4.'
ieee: 'G. Pandit, M. Röder, and A.-C. Ngonga Ngomo, “Evaluating Approximate Nearest
Neighbour Search Systems on Knowledge Graph Embeddings,” in Lecture Notes in
Computer Science, Cham: Springer Nature Switzerland, 2025.'
mla: Pandit, Gaurav, et al. “Evaluating Approximate Nearest Neighbour Search Systems
on Knowledge Graph Embeddings.” Lecture Notes in Computer Science, Springer
Nature Switzerland, 2025, doi:10.1007/978-3-031-94575-5_4.
short: 'G. Pandit, M. Röder, A.-C. Ngonga Ngomo, in: Lecture Notes in Computer Science,
Springer Nature Switzerland, Cham, 2025.'
date_created: 2026-01-06T09:53:58Z
date_updated: 2026-01-06T09:55:26Z
department:
- _id: '574'
- _id: '923'
doi: 10.1007/978-3-031-94575-5_4
language:
- iso: eng
place: Cham
publication: Lecture Notes in Computer Science
publication_identifier:
isbn:
- '9783031945748'
- '9783031945755'
issn:
- 0302-9743
- 1611-3349
publication_status: published
publisher: Springer Nature Switzerland
status: public
title: Evaluating Approximate Nearest Neighbour Search Systems on Knowledge Graph
Embeddings
type: book_chapter
user_id: '67199'
year: '2025'
...