---
_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: <i>Proceedings of the 24th International Semantic
    Web Conference (ISWC 2025)</i>. Springer, Cham; 2025:pp 41-56. doi:<a href="https://doi.org/10.1007/978-3-032-09530-5_3">https://doi.org/10.1007/978-3-032-09530-5_3</a>'
  apa: Moteu Ngoli, T., Kouagou, N. J., Zahera, H. M. A., &#38; Ngonga Ngomo, A.-C.
    (2025). Benchmarking Knowledge Editing using Logical Rules. <i>Proceedings of
    the 24th International Semantic Web Conference (ISWC 2025)</i>, pp 41-56. <a href="https://doi.org/10.1007/978-3-032-09530-5_3">https://doi.org/10.1007/978-3-032-09530-5_3</a>
  bibtex: '@inproceedings{Moteu Ngoli_Kouagou_Zahera_Ngonga Ngomo_2025, title={Benchmarking
    Knowledge Editing using Logical Rules}, DOI={<a href="https://doi.org/10.1007/978-3-032-09530-5_3">https://doi.org/10.1007/978-3-032-09530-5_3</a>},
    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 <i>Proceedings of the 24th International Semantic Web Conference (ISWC 2025)</i>,
    pp 41-56. Springer, Cham, 2025. <a href="https://doi.org/10.1007/978-3-032-09530-5_3">https://doi.org/10.1007/978-3-032-09530-5_3</a>.
  ieee: 'T. Moteu Ngoli, N. J. Kouagou, H. M. A. Zahera, and A.-C. Ngonga Ngomo, “Benchmarking
    Knowledge Editing using Logical Rules,” in <i>Proceedings of the 24th International
    Semantic Web Conference (ISWC 2025)</i>, Nara, Japan, 2025, p. pp 41-56, doi:
    <a href="https://doi.org/10.1007/978-3-032-09530-5_3">https://doi.org/10.1007/978-3-032-09530-5_3</a>.'
  mla: Moteu Ngoli, Tatiana, et al. “Benchmarking Knowledge Editing Using Logical
    Rules.” <i>Proceedings of the 24th International Semantic Web Conference (ISWC
    2025)</i>, Springer, Cham, 2025, p. pp 41-56, doi:<a href="https://doi.org/10.1007/978-3-032-09530-5_3">https://doi.org/10.1007/978-3-032-09530-5_3</a>.
  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'
...