Lune

EMNLP Findings2024

Editing Conceptual Knowledge for Large Language Models

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

Abstract

Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs). Current approaches and evaluations merely explore 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 definitions 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

21 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors cites Locating and Editing Factual Associations in GPT
  • Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors cites Language Models are Few-Shot Learners
  • Locating and Editing Factual Associations in GPT cites Language Models are Few-Shot Learners
  • Keys to Robust Edits: From Theoretical Insights to Practical Advances cites Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  • Keys to Robust Edits: From Theoretical Insights to Practical Advances cites PMET: Precise Model Editing in a Transformer
  • MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA cites Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  • MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA cites Locating and Editing Factual Associations in GPT
  • Can Editing LLMs Inject Harm? cites Locating and Editing Factual Associations in GPT
  • Can Editing LLMs Inject Harm? cites PMET: Precise Model Editing in a Transformer
  • Disentangling Knowledge Representations for Large Language Model Editing cites Locating and Editing Factual Associations in GPT
  • Disentangling Knowledge Representations for Large Language Model Editing cites MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA
  • Personality Vector: Modulating Personality of Large Language Models by Model Merging cites Locating and Editing Factual Associations in GPT
  • PMET: Precise Model Editing in a Transformer cites Locating and Editing Factual Associations in GPT
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers21

  1. Can Editing LLMs Inject Harm?Canyu Chen, Baixiang Huang, Zekun Li, Zhaorun Chen et al.AAAI 2026 · 26 citations
  2. Sharpness-Aware Pretraining Mitigates Catastrophic ForgettingIshaan Watts, Catherine Li, Sachin Goyal, Jacob Mitchell Springer et al.ICML 2026 · 6 citations
  3. Disentangling Knowledge Representations for Large Language Model EditingMengqi Zhang, Zisheng Zhou, Xiaotian Ye, Qiang Liu et al.ICLR 2026 · 6 citations
  4. Personality Vector: Modulating Personality of Large Language Models by Model MergingSeungjong Sun, Seo Yeon Baek, Jang Hyun KimEMNLP 2025 · 5 citations
  5. Keys to Robust Edits: From Theoretical Insights to Practical AdvancesJianhao Yan, Futing Wang, Yun Luo, Yafu Li et al.ACL 2025 · 3 citations

Builds on33

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Locating and Editing Factual Associations in GPTKevin Meng, David Bau, Alex Andonian, Yonatan BelinkovNeurIPS 2022 · 3,415 citations
  3. Aging with GRACE: Lifelong Model Editing with Discrete Key-Value AdaptorsTom Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim et al.NeurIPS 2023 · 349 citations
  4. PMET: Precise Model Editing in a TransformerXiaopeng Li, Shasha Li, Shezheng Song, Jing Yang et al.AAAI 2024 · 208 citations
  5. MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRALang Yu, Qin Chen, Jie Zhou, Liang HeAAAI 2024 · 96 citations

Related papers

  1. RelEdit: Evaluating Conceptual Knowledge Editing in Language Models via Relational ReasoningYifan Niu, Miao Peng, Nuo Chen, Yatao Bian et al.ACL Findings 2025
  2. Unveiling the Pitfalls of Knowledge Editing for Large Language ModelsZhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang et al.ICLR 2024 · 47 citations
  3. Can We Edit Multimodal Large Language Models?Siyuan Cheng, Bozhong Tian, Qingbin Liu, Xi Chen et al.EMNLP 2023 · 16 citations
  4. Can Knowledge Editing Really Correct Hallucinations?Baixiang Huang, Canyu Chen, Xiongxiao Xu, Ali Payani et al.ICLR 2025
  5. Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language ModelsCheng-Hsun Hsueh, Paul Kuo-Ming Huang, Tzu-Han Lin, Che-Wei Liao et al.EMNLP Findings 2024 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines