EMNLP Findings2023
Emptying the Ocean with a Spoon: Should We Edit Models?
Yuval Pinter, Michael Elhadad
Abstract
We call into question the recently popularized method of direct model editing as a means of correcting factual errors in LLM generations. We contrast model editing with three similar but distinct approaches that pursue better defined objectives: (1) retrieval-based architectures, which decouple factual memory from inference and linguistic capabilities embodied in LLMs;
(2) concept erasure methods, which aim at preventing systemic bias in generated text; and (3) attribution methods, which aim at grounding generations into identified textual sources.
We argue that direct model editing cannot be trusted as a systematic remedy for the disadvantages inherent to LLMs, and while it has proven potential in improving model explainability, it opens risks by reinforcing the notion that models can be trusted for factuality. We call for cautious promotion and application of model editing as part of the LLM deployment process, and for responsibly limiting the use cases of LLMs to those not relying on editing as a critical component.
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.
6 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
- Revealing and Mitigating Over-Attention in Knowledge Editing cites Locating and Editing Factual Associations in GPT
- Locating and Editing Factual Associations in GPT cites Language Models are Few-Shot Learners
- Improving Language Models by Retrieving from Trillions of Tokens cites Language Models are Few-Shot Learners
- Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence cites Language Models are Few-Shot Learners
- Knowledge Conflicts for LLMs: A Survey cites Locating and Editing Factual Associations in GPT
- Knowledge Conflicts for LLMs: A Survey cites Improving Language Models by Retrieving from Trillions of Tokens
- Knowledge Conflicts for LLMs: A Survey cites Language Models are Few-Shot Learners
- Knowledge Conflicts for LLMs: A Survey cites Training language models to follow instructions with human feedback
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model cites Language Models are Few-Shot Learners
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model cites Training language models to follow instructions with human feedback
- Knowledge Localization: Mission Not Accomplished? Enter Query Localization! cites Locating and Editing Factual Associations in GPT
- Training language models to follow instructions with human feedback cites Language Models are Few-Shot Learners
Cited by top-tier papers6
- Knowledge Conflicts for LLMs: A SurveyRongwu Xu, Zehan Qi, Zhijiang Guo, Cunxiang Wang et al.EMNLP 2024 · 38 citations
- Revealing and Mitigating Over-Attention in Knowledge EditingPinzheng Wang, Zecheng Tang, Keyan Zhou, Juntao Li et al.ICLR 2025
- Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical EvidenceWanying Ren, Xin Song, Futing Wang, Guoxiu He et al.ICML 2026
- Towards Scalable Lifelong Knowledge Editing with Selective Knowledge SuppressionDahyun Jung, Jaewook Lee, Heuiseok LimACL 2026
- Knowledge Localization: Mission Not Accomplished? Enter Query Localization!Yuheng Chen, Pengfei Cao, Yubo Chen, Kang Liu et al.ICLR 2025
Builds on25
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- Locating and Editing Factual Associations in GPTKevin Meng, David Bau, Alex Andonian, Yonatan BelinkovNeurIPS 2022 · 3,415 citations
- Improving Language Models by Retrieving from Trillions of TokensSebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai et al.ICML 2022 · 1,629 citations
Related papers
- 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 We Debias Multimodal Large Language Models via Model Editing?Zecheng Wang, Xinye Li, Zhanyue Qin, Chunshan Li et al.ACM MM 2024 · 2 citations
- Tracing and Reversing Edits in LLMsPaul Youssef, Zhixue Zhao, Christin Seifert, Jörg SchlöttererICLR 2026 · 7 citations
- Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language ModelsZihao Lin, Mohammad Beigi, Hongxuan Li, Yufan Zhou et al.ACL 2024 · 1 citation
- Memory-Based Model Editing at ScaleEric Mitchell, Charles Lin, Antoine Bosselut, Christopher D. Manning et al.ICML 2022 · 520 citations
