ACL Findings2025
Context-Robust Knowledge Editing for Language Models
Haewon Park, Gyubin Choi, Minjun Kim, Yohan Jo
Abstract
Knowledge editing (KE) methods offer an efficient way to modify knowledge in large language models. Current KE evaluations typically assess editing success by considering only the edited knowledge without any preceding contexts. In real-world applications, however, preceding contexts often trigger the retrieval of the original knowledge and undermine the intended edit. To address this issue, we have developed CHED-a benchmark designed to evaluate the context robustness of KE methods. Evaluations on CHED show that they often fail when preceding contexts are present. To mitigate this shortcoming, we introduce CoRE, a KE method designed to strengthen context robustness by minimizing context-sensitive variance in hidden states of the model for edited knowledge. This method not only improves the editing success rate in situations where a preceding context is present but also preserves the overall capabilities of the model. We also provide an in-depth analysis of the differing impacts of preceding contexts when introduced as user utterances versus assistant responses, and we dissect attention-score patterns to assess how specific tokens influence editing success. Our dataset and code are available at https://github.com/holi-lab/CoRE.
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.
3 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 Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
- SUIT: Knowledge Editing with Subspace-Aware Key-Value Mappings cites Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
- SUIT: Knowledge Editing with Subspace-Aware Key-Value Mappings cites Measuring Massive Multitask Language Understanding
- KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning cites Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
- KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning cites Measuring Massive Multitask Language Understanding
Cited by top-tier papers3
- KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and UnlearningYinyi Luo, Zhexian Zhou, Hao Chen, Kai Qiu et al.ICLR 2026 · 4 citations
- 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
- SUIT: Knowledge Editing with Subspace-Aware Key-Value MappingsHaewon Park, Sangwoo Kim, Yohan JoICLR 2026
Builds on19
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
- G-Eval: NLG Evaluation using Gpt-4 with Better Human AlignmentYang Liu, Dan Iter, Yichong Xu, Shuohang Wang et al.EMNLP 2023 · 549 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
Related papers
- ScEdit: Script-based Assessment of Knowledge EditingXinye Li, Zunwen Zheng, Qian Zhang, Dekai Zhuang et al.ACL Findings 2025
- COMPKE: Complex Question Answering under Knowledge EditingKeyuan Cheng, Zijian Kan, Zhuoran Zhang, Muhammad Asif Ali et al.ACL Findings 2025 · 1 citation
- Towards Meta-Cognitive Knowledge Editing for Multimodal LLMsZhaoyu Fan, Kaihang Pan, Mingze Zhou, Bosheng Qin et al.WWW 2026
- Can Knowledge Editing Really Correct Hallucinations?Baixiang Huang, Canyu Chen, Xiongxiao Xu, Ali Payani et al.ICLR 2025
- Editing Conceptual Knowledge for Large Language ModelsXiaohan Wang, Shengyu Mao, Shumin Deng, Yunzhi Yao et al.EMNLP Findings 2024 · 9 citations
