EMNLP Findings2024
Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
Cheng-Hsun Hsueh, Paul Kuo-Ming Huang, Tzu-Han Lin, Che-Wei Liao, Hung-Chieh Fang, Chao-Wei Huang, Yun-Nung Chen
Abstract
Knowledge editing is a rising technique for efficiently updating factual knowledge in large language models (LLMs) with minimal alteration of parameters. However, recent studies have identified side effects, such as knowledge distortion and the deterioration of general abilities, that have emerged after editing. Despite these findings, evaluating the pitfalls of knowledge editing often relies on inconsistent metrics and benchmarks, lacking a uniform standard. In response, this survey presents a comprehensive study of these side effects, providing a unified perspective on the challenges of knowledge editing in LLMs by conducting experiments with consistent metrics and benchmarks. Additionally, we review related works and outline potential research directions to address these limitations. Our survey highlights the limitations of current knowledge editing methods, emphasizing the need for a deeper understanding of the inner knowledge structures of LLMs and improved knowledge editing methods. To foster future research, we have released the complementary materials publicly 1 .
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.
9 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
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 Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
- Scaling Knowledge Editing in LLMs to 100, 000 Facts with Neural KV Database cites Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
- Scaling Knowledge Editing in LLMs to 100, 000 Facts with Neural KV Database cites Locating and Editing Factual Associations in GPT
- Scaling Knowledge Editing in LLMs to 100, 000 Facts with Neural KV Database cites PMET: Precise Model Editing in a Transformer
- CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners cites Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
- CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners cites Locating and Editing Factual Associations in GPT
- CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners cites Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
- CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners cites Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries
- 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
- Precise In-Parameter Concept Erasure in Large Language Models cites Locating and Editing Factual Associations in GPT
- Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries cites Locating and Editing Factual Associations in GPT
- PMET: Precise Model Editing in a Transformer cites Locating and Editing Factual Associations in GPT
Cited by top-tier papers9
- Can Editing LLMs Inject Harm?Canyu Chen, Baixiang Huang, Zekun Li, Zhaorun Chen et al.AAAI 2026 · 26 citations
- Precise In-Parameter Concept Erasure in Large Language ModelsYoav Gur-Arieh, Clara Suslik, Yihuai Hong, Fazl Barez et al.EMNLP 2025 · 10 citations
- Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop QueriesEden Biran, Daniela Gottesman, Sohee Yang, Mor Geva et al.EMNLP 2024 · 3 citations
- Scaling Knowledge Editing in LLMs to 100, 000 Facts with Neural KV DatabaseWeizhi Fei, Hao Shi, Jing Xu, Jingchen Peng et al.ICLR 2026 · 2 citations
- CaKE: Circuit-aware Editing Enables Generalizable Knowledge LearnersYunzhi Yao, Jizhan Fang, Jia-Chen Gu, Ningyu Zhang et al.EMNLP 2025 · 1 citation
Builds on23
- Locating and Editing Factual Associations in GPTKevin Meng, David Bau, Alex Andonian, Yonatan BelinkovNeurIPS 2022 · 3,415 citations
- PIQA: Reasoning about Physical Commonsense in Natural LanguageYonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao et al.AAAI 2020 · 2,916 citations
- Aging with GRACE: Lifelong Model Editing with Discrete Key-Value AdaptorsTom Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim et al.NeurIPS 2023 · 349 citations
- Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language ModelsPeter Hase, Mohit Bansal, Been Kim, Asma GhandehariounNeurIPS 2023 · 307 citations
- PMET: Precise Model Editing in a TransformerXiaopeng Li, Shasha Li, Shezheng Song, Jing Yang et al.AAAI 2024 · 208 citations
Related papers
- Unveiling the Pitfalls of Knowledge Editing for Large Language ModelsZhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang et al.ICLR 2024 · 47 citations
- Should We Really Edit Language Models? On the Evaluation of Edited Language ModelsQi Li, Xiang Liu, Zhenheng Tang, Peijie Dong et al.NeurIPS 2024 · 25 citations
- Editing Across Languages: A Survey of Multilingual Knowledge EditingNadir Durrani, Basel Mousi, Fahim DalviEMNLP 2025
- Model Editing Harms General Abilities of Large Language Models: Regularization to the RescueJia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu et al.EMNLP 2024 · 8 citations
- Can Knowledge Editing Really Correct Hallucinations?Baixiang Huang, Canyu Chen, Xiongxiao Xu, Ali Payani et al.ICLR 2025
