---
_id: '60958'
abstract:
- lang: eng
  text: Large Language Models (LLMs) excel in understanding, generating, and processing
    human language, with growing adoption in process mining. Process mining relies
    on event logs that capture explicit process knowledge; however, knowledge-intensive
    processes (KIPs) in domains such as healthcare and product development depend
    on tacit knowledge, which is often absent from event logs. To bridge this gap,
    this study proposes a LLM-based framework for mobilizing tacit process knowledge
    and enriching event logs. A proof-of-concept is demonstrated using a KIP-specific
    LLM-driven conversational agent built on GPT-4o. The results indicate that LLMs
    can capture tacit process knowledge through targeted queries and systematically
    integrate it into event logs. This study presents a novel approach combining LLMs,
    knowledge management, and process mining, advancing the understanding and management
    of KIPs by enhancing knowledge accessibility and documentation.
author:
- first_name: Katharina
  full_name: Brennig, Katharina
  last_name: Brennig
citation:
  ama: 'Brennig K. Revealing the Unspoken: Using LLMs to Mobilize and Enrich Tacit
    Knowledge in Event Logs of Knowledge-Intensive Processes. In: <i>AMCIS 2025 Proceedings.
    11.</i> ; 2025.'
  apa: 'Brennig, K. (2025). Revealing the Unspoken: Using LLMs to Mobilize and Enrich
    Tacit Knowledge in Event Logs of Knowledge-Intensive Processes. <i>AMCIS 2025
    Proceedings. 11.</i> Americas Conference on Information Systems, Montréal.'
  bibtex: '@inproceedings{Brennig_2025, title={Revealing the Unspoken: Using LLMs
    to Mobilize and Enrich Tacit Knowledge in Event Logs of Knowledge-Intensive Processes},
    booktitle={AMCIS 2025 Proceedings. 11.}, author={Brennig, Katharina}, year={2025}
    }'
  chicago: 'Brennig, Katharina. “Revealing the Unspoken: Using LLMs to Mobilize and
    Enrich Tacit Knowledge in Event Logs of Knowledge-Intensive Processes.” In <i>AMCIS
    2025 Proceedings. 11.</i>, 2025.'
  ieee: 'K. Brennig, “Revealing the Unspoken: Using LLMs to Mobilize and Enrich Tacit
    Knowledge in Event Logs of Knowledge-Intensive Processes,” presented at the Americas
    Conference on Information Systems, Montréal, 2025.'
  mla: 'Brennig, Katharina. “Revealing the Unspoken: Using LLMs to Mobilize and Enrich
    Tacit Knowledge in Event Logs of Knowledge-Intensive Processes.” <i>AMCIS 2025
    Proceedings. 11.</i>, 2025.'
  short: 'K. Brennig, in: AMCIS 2025 Proceedings. 11., 2025.'
conference:
  end_date: 2025-08-16
  location: Montréal
  name: Americas Conference on Information Systems
  start_date: 2025-08-14
date_created: 2025-08-20T07:03:37Z
date_updated: 2025-08-20T07:06:16Z
department:
- _id: '196'
keyword:
- Process Mining
- Large Language Model
- Knowledge Management
- Knowledge-Intensive Process
- Tacit Knowledge
language:
- iso: eng
main_file_link:
- url: https://aisel.aisnet.org/amcis2025/sig_svc/sig_svc/11/
publication: AMCIS 2025 Proceedings. 11.
related_material:
  link:
  - relation: confirmation
    url: https://aisel.aisnet.org/amcis2025/sig_svc/sig_svc/11/
status: public
title: 'Revealing the Unspoken: Using LLMs to Mobilize and Enrich Tacit Knowledge
  in Event Logs of Knowledge-Intensive Processes'
type: conference
user_id: '51905'
year: '2025'
...
---
_id: '62701'
abstract:
- lang: eng
  text: 'Learning  continuous  vector  representations  for  knowledge graphs has
    significantly improved state-of-the-art performances in many challenging tasks.
    Yet, deep-learning-based models are only post-hoc and locally explainable. In
    contrast, learning Web Ontology Language (OWL) class  expressions  in  Description  Logics  (DLs)  is  ante-hoc  and  globally
    explainable. However, state-of-the-art learners have two well-known lim-itations:  scaling  to  large  knowledge  graphs  and  handling  missing  infor-mation.  Here,  we  present  a  decision-tree-based  learner  (tDL)  to  learn
    Web  Ontology  Languages  (OWLs)  class  expressions  over  large  knowl-edge
    graphs, while imputing missing triples. Given positive and negative example individuals,
    tDL  firstly constructs unique OWL expressions in .SHOIN from  concise  bounded  descriptions  of  individuals.  Each  OWL
    class expression is used as a feature in a binary classification problem to represent
    input individuals. Thereafter, tDL  fits a CART decision tree to learn Boolean
    decision rules distinguishing positive examples from nega-tive examples. A final
    OWL expression in.SHOIN is built by traversing the  built  CART  decision  tree  from  the  root  node  to  leaf  nodes  for  each
    positive example. By this, tDL  can learn OWL class expressions without exploration,
    i.e., the number of queries to a knowledge graph is bounded by the number of input
    individuals. Our empirical results show that tDL outperforms  the  current state-of-the-art  models  across
    datasets. Impor-tantly, our experiments over a large knowledge graph (DBpedia
    with 1.1 billion triples) show that tDL  can effectively learn accurate OWL class
    expressions,  while  the  state-of-the-art  models  fail  to  return  any  results.
    Finally,  expressions  learned  by  tDL  can  be  seamlessly  translated  into
    natural language explanations using a pre-trained large language model and a DL
    verbalizer.'
author:
- first_name: Caglar
  full_name: Demir, Caglar
  last_name: Demir
- first_name: Moshood
  full_name: Yekini, Moshood
  last_name: Yekini
- first_name: Michael
  full_name: Röder, Michael
  last_name: Röder
- first_name: Yasir
  full_name: Mahmood, Yasir
  last_name: Mahmood
- first_name: Axel-Cyrille
  full_name: Ngonga Ngomo, Axel-Cyrille
  last_name: Ngonga Ngomo
citation:
  ama: 'Demir C, Yekini M, Röder M, Mahmood Y, Ngonga Ngomo A-C. Tree-Based OWL Class
    Expression Learner over Large Graphs. In: <i>Lecture Notes in Computer Science</i>.
    Springer Nature Switzerland; 2025. doi:<a href="https://doi.org/10.1007/978-3-032-06066-2_29">10.1007/978-3-032-06066-2_29</a>'
  apa: Demir, C., Yekini, M., Röder, M., Mahmood, Y., &#38; Ngonga Ngomo, A.-C. (2025).
    Tree-Based OWL Class Expression Learner over Large Graphs. In <i>Lecture Notes
    in Computer Science</i>. European Conference on Machine Learning and Principles
    and Practice of Knowledge Discovery in Databases - ECML PKDD, Porto, Portugal.
    Springer Nature Switzerland. <a href="https://doi.org/10.1007/978-3-032-06066-2_29">https://doi.org/10.1007/978-3-032-06066-2_29</a>
  bibtex: '@inbook{Demir_Yekini_Röder_Mahmood_Ngonga Ngomo_2025, place={Cham}, title={Tree-Based
    OWL Class Expression Learner over Large Graphs}, DOI={<a href="https://doi.org/10.1007/978-3-032-06066-2_29">10.1007/978-3-032-06066-2_29</a>},
    booktitle={Lecture Notes in Computer Science}, publisher={Springer Nature Switzerland},
    author={Demir, Caglar and Yekini, Moshood and Röder, Michael and Mahmood, Yasir
    and Ngonga Ngomo, Axel-Cyrille}, year={2025} }'
  chicago: 'Demir, Caglar, Moshood Yekini, Michael Röder, Yasir Mahmood, and Axel-Cyrille
    Ngonga Ngomo. “Tree-Based OWL Class Expression Learner over Large Graphs.” In
    <i>Lecture Notes in Computer Science</i>. Cham: Springer Nature Switzerland, 2025.
    <a href="https://doi.org/10.1007/978-3-032-06066-2_29">https://doi.org/10.1007/978-3-032-06066-2_29</a>.'
  ieee: 'C. Demir, M. Yekini, M. Röder, Y. Mahmood, and A.-C. Ngonga Ngomo, “Tree-Based
    OWL Class Expression Learner over Large Graphs,” in <i>Lecture Notes in Computer
    Science</i>, Cham: Springer Nature Switzerland, 2025.'
  mla: Demir, Caglar, et al. “Tree-Based OWL Class Expression Learner over Large Graphs.”
    <i>Lecture Notes in Computer Science</i>, Springer Nature Switzerland, 2025, doi:<a
    href="https://doi.org/10.1007/978-3-032-06066-2_29">10.1007/978-3-032-06066-2_29</a>.
  short: 'C. Demir, M. Yekini, M. Röder, Y. Mahmood, A.-C. Ngonga Ngomo, in: Lecture
    Notes in Computer Science, Springer Nature Switzerland, Cham, 2025.'
conference:
  end_date: 2025-09-19
  location: Porto, Portugal
  name: European Conference on Machine Learning and Principles and Practice of Knowledge
    Discovery in Databases - ECML PKDD
  start_date: 2025-09-15
date_created: 2025-11-28T14:09:17Z
date_updated: 2025-11-28T14:57:39Z
department:
- _id: '34'
- _id: '574'
doi: 10.1007/978-3-032-06066-2_29
keyword:
- Decision Tree
- OWL Class Expression Learning
- Description Logic
- Knowledge Graph
- Large Language Model
- Verbalizer
language:
- iso: eng
place: Cham
project:
- _id: '285'
  name: SAIL - Nachhaltiger Lebenszyklus von intelligenten soziotechnischen Systemen
publication: Lecture Notes in Computer Science
publication_identifier:
  isbn:
  - '9783032060655'
  - '9783032060662'
  issn:
  - 0302-9743
  - 1611-3349
publication_status: published
publisher: Springer Nature Switzerland
status: public
title: Tree-Based OWL Class Expression Learner over Large Graphs
type: book_chapter
user_id: '114533'
year: '2025'
...