EMNLP 2024finding17 citations

Editing Conceptual Knowledge for Large Language Models

Xiaohan Wang, Shengyu Mao, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Abstract

Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs). Current approaches and evaluations merely explore the instance-level editing, while whether LLMs possess the capability to modify concepts remains unclear. This paper pioneers the investigation of editing conceptual knowledge for LLMs, by constructing a novel benchmark dataset ConceptEdit and establishing a suite of new metrics for evaluation. The experimental results reveal that, although existing editing methods can efficiently modify concept-level definition to some extent, they also have the potential to distort the related instantial knowledge in LLMs, leading to poor performance. We anticipate this work can inspire further progress in understanding LLMs.

BibTeX
@inproceedings{wang-etal-2024-editing,
    title = "Editing Conceptual Knowledge for Large Language Models",
    author = "Wang, Xiaohan  and
      Mao, Shengyu  and
      Deng, Shumin  and
      Yao, Yunzhi  and
      Shen, Yue  and
      Liang, Lei  and
      Gu, Jinjie  and
      Chen, Huajun  and
      Zhang, Ningyu",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.40/",
    doi = "10.18653/v1/2024.findings-emnlp.40",
    pages = "706--724"
}
Editing Conceptual Knowledge for Large Language Models · EMNLP 2024