---
res:
  bibo_abstract:
  - 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.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Tatiana
      foaf_name: Moteu Ngoli, Tatiana
      foaf_surname: Moteu Ngoli
      foaf_workInfoHomepage: http://www.librecat.org/personId=99174
  - foaf_Person:
      foaf_givenName: N'Dah Jean
      foaf_name: Kouagou, N'Dah Jean
      foaf_surname: Kouagou
      foaf_workInfoHomepage: http://www.librecat.org/personId=87189
  - foaf_Person:
      foaf_givenName: Hamada Mohamed Abdelsamee
      foaf_name: Zahera, Hamada Mohamed Abdelsamee
      foaf_surname: Zahera
      foaf_workInfoHomepage: http://www.librecat.org/personId=72768
    orcid: 0000-0003-0215-1278
  - foaf_Person:
      foaf_givenName: Axel-Cyrille
      foaf_name: Ngonga Ngomo, Axel-Cyrille
      foaf_surname: Ngonga Ngomo
      foaf_workInfoHomepage: http://www.librecat.org/personId=65716
  bibo_doi: https://doi.org/10.1007/978-3-032-09530-5_3
  dct_date: 2025^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/978-3-032-09530-5
  dct_language: eng
  dct_publisher: Springer, Cham@
  dct_subject:
  - dice sailproject moteu kouagou zahera ngonga
  dct_title: Benchmarking Knowledge Editing using Logical Rules@
...