---
title: "CaPEdit — paper by Wu et al. (2026) — summary and ideas"
description: "It builds on an RL-trained hypernetwork in the style of RLEdit and follows a generate-then-edit scheme. 36 references."
authors: ["Song-Li Wu", "Zhaocheng Du", "Xianquan Wang", "Jingyi Wang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.770/"
doi: "10.18653/v1/2026.findings-acl.770"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wu-2026-capedit-capability-preserving-lifelong-knowledge/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2026-capedit-capability-preserving-lifelong-knowledge/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/) / CaPEdit: Capability-Preserving Lifelong Knowledge Editing For Language Models

# CaPEdit: Capability-Preserving Lifelong Knowledge Editing For Language Models

**Authors:** [Song-Li Wu](https://md.research.elamur.ai/free/en/authors/song-li-wu/), [Zhaocheng Du](https://md.research.elamur.ai/free/en/authors/zhaocheng-du/), [Xianquan Wang](https://md.research.elamur.ai/free/en/authors/xianquan-wang/) and [Jingyi Wang](https://md.research.elamur.ai/free/en/authors/jingyi-wang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.770/) · [PDF](https://aclanthology.org/2026.findings-acl.770.pdf) · [DOI 10.18653/v1/2026.findings-acl.770](https://doi.org/10.18653/v1/2026.findings-acl.770) · [OpenAlex](https://openalex.org/W7166860107)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Repeatedly editing facts in a large language model, known as lifelong knowledge editing (LKE), tends to wear down its broader abilities over time. Earlier fixes mostly cap the size of parameter changes, which limits how well new knowledge is absorbed. The authors argue that much of the damage comes from a timing problem. Factual knowledge can be changed quickly and locally. Procedural knowledge, which governs how facts are retrieved, reasoned over and applied, is spread across many related facts and shifts more slowly.

CaPEdit treats editing as a two-speed process. It builds on an RL-trained hypernetwork in the style of RLEdit and follows a generate-then-edit scheme. First it synthesizes procedural signals from the stream of edits. Then it predicts weight updates using two rewards: a fast one for factual correction and a slow, smoothed one for procedural consistency. Training combines per-step updates with optimization over whole edit trajectories.

Across several LLMs and benchmarks, CaPEdit keeps core capabilities far better than prior editors while editing accurately and quickly. This matters for models that must be kept current without full retraining.

## Key points
- **Capability gains and speed:** CaPEdit improves capability preservation by 49.78% across memorization, reasoning, generalization and diversification. Compared with most current methods, it completes edits in just 18.07% of the time.
- **Procedural signals:** three are synthesized, namely memory-consistent retrieval (backed by a buffer of earlier edits), reasoning trajectories and contextual adaptation. The slow procedural reward is EMA-smoothed.
- **Evaluation setup:** experiments use LLaMA-3-8B and Gemma-2 on benchmarks including FEVER, with cross-domain tests adding the Wiki dataset. Editing quality is measured by Edit Success, Portability, Locality and Fluency.
- **Long edit sequences:** capabilities stay largely intact up to 40,000 edits. Baselines compared include MEND, AlphaEdit, MALMEN, DAFNet, AnyEdit, RLEdit and ENCORE.
- **Ablation and plug-in use:** removing procedural synthesis cuts editing accuracy by over 40% and capability retention by over 50% on average. Added as a plug-in module, CaPEdit improves MEND, MALMEN, DAFNet and RLEdit.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 415 works · 94,028 citations
- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 145 works · 114,409 citations
- [Huawei Technologies](https://md.research.elamur.ai/free/en/companies/huawei-technologies/) — Company, Shenzhen, China · 96 works · 15,432 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Song-Li Wu, Zhaocheng Du, Xianquan Wang and Jingyi Wang. 2026. CaPEdit: Capability-Preserving Lifelong Knowledge Editing For Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wu2026capedit,
  title = {{CaPEdit: Capability-Preserving Lifelong Knowledge Editing For Language Models}},
  author = {Song-Li Wu, Zhaocheng Du, Xianquan Wang and Jingyi Wang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.770},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.770}
}
```

- [← previous Capability Decomposition for Unified Information Extraction via Hierarchical Mixture-of-Experts](https://md.research.elamur.ai/free/en/papers/zhou-2026-capability-decomposition-unified-information-extraction/)
- [next → CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models](https://md.research.elamur.ai/free/en/papers/zhou-2026-capruner-conceptual-adjacent-scene-graph/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/)

## References

36 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Albrecht Böttcher and David Wenzel. 2008. The frobenius norm and the commutator. Linear algebra and its applications, 429(8-9):1864–1885. [find](https://scholar.google.com/scholar?q=Albrecht+B%C3%B6ttcher+and+David+Wenzel%2E+2008%2E+The+frobenius+norm+and+the+commutator%2E+Linear+algebra+and+its+applications%2C+429%288%2D9%29%3A1864%E2%80%931885%2E)
2. Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, and Mor Geva. 2024. Evaluating the ripple effects of knowledge editing in language models. Transactions of the Association for Computational Linguistics, 12:283–298. [find](https://scholar.google.com/scholar?q=Roi+Cohen%2C+Eden+Biran%2C+Ori+Yoran%2C+Amir+Globerson%2C+and+Mor+Geva%2E+2024%2E+Evaluating+the+ripple+effects+of+knowledge+editing+in+language+models%2E+Transactions+of+the+Association+for+Computational+Linguisti)
3. Jingcheng Deng, Zihao Wei, Liang Pang, Hanxing Ding, Huawei Shen, and Xueqi Cheng. 2025. Everything is editable: Extend knowledge editing to unstructured data in large language models. In ICLR. [find](https://scholar.google.com/scholar?q=Jingcheng+Deng%2C+Zihao+Wei%2C+Liang+Pang%2C+Hanxing+Ding%2C+Huawei+Shen%2C+and+Xueqi+Cheng%2E+2025%2E+Everything+is+editable%3A+Extend+knowledge+editing+to+unstructured+data+in+large+language+models%2E+In+ICLR%2E)
4. Qingxiu Dong, Damai Dai, Yifan Song, Jingjing Xu, Zhifang Sui, and Lei Li. 2022. [Calibrating factual knowledge in pretrained language models](https://md.research.elamur.ai/free/en/papers/dong-2022-calibrating-factual-knowledge-pretrained-language/). arXiv preprint arXiv:2210.03329.
5. Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Jie Shi, Xiang Wang, Xiangnan He, and Tat-Seng Chua. 2025. Alphaedit: Null-space constrained knowledge editing for language models. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Junfeng+Fang%2C+Houcheng+Jiang%2C+Kun+Wang%2C+Yunshan+Ma%2C+Jie+Shi%2C+Xiang+Wang%2C+Xiangnan+He%2C+and+Tat%2DSeng+Chua%2E+2025%2E+Alphaedit%3A+Null%2Dspace+constrained+knowledge+editing+for+language+models%2E+In+The+Thirteent)
6. Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, and Jonathan Berant. 2021. Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies. Transactions of the Association for Computational Linguistics, 9:346– 361. [find](https://scholar.google.com/scholar?q=Mor+Geva%2C+Daniel+Khashabi%2C+Elad+Segal%2C+Tushar+Khot%2C+Dan+Roth%2C+and+Jonathan+Berant%2E+2021%2E+Did+aristotle+use+a+laptop%3F+a+question+answering+benchmark+with+implicit+reasoning+strategies%2E+Transactions+of+)
7. Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, and Nanyun Peng. 2024. [Model editing harms general abilities of large language models: Regularization to the rescue](https://md.research.elamur.ai/free/en/papers/gu-2024-model-editing-harms-general-abilities/). arXiv preprint arXiv:2401.04700.
8. Akshat Gupta, Phudish Prateepamornkul, Maochuan Lu, Ahmed Alaa, Thomas Hartvigsen, and Gopala Anumanchipalli. 2025. Lifelong sequential knowledge editing without model degradation. arXiv e-prints, pages arXiv–2502. [find](https://scholar.google.com/scholar?q=Akshat+Gupta%2C+Phudish+Prateepamornkul%2C+Maochuan+Lu%2C+Ahmed+Alaa%2C+Thomas+Hartvigsen%2C+and+Gopala+Anumanchipalli%2E+2025%2E+Lifelong+sequential+knowledge+editing+without+model+degradation%2E+arXiv+e%2Dprints%2C+pag)
9. Tom Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim, and Marzyeh Ghassemi. 2023. Aging with grace: Lifelong model editing with discrete key-value adaptors. Advances in Neural Information Processing Systems, 36:47934–47959. [find](https://scholar.google.com/scholar?q=Tom+Hartvigsen%2C+Swami+Sankaranarayanan%2C+Hamid+Palangi%2C+Yoon+Kim%2C+and+Marzyeh+Ghassemi%2E+2023%2E+Aging+with+grace%3A+Lifelong+model+editing+with+discrete+key%2Dvalue+adaptors%2E+Advances+in+Neural+Information+P)
10. Houcheng Jiang, Junfeng Fang, Ningyu Zhang, Mingyang Wan, Guojun Ma, Xiang Wang, Xiangnan He, and Tat-Seng Chua. 2025. Anyedit: Edit any knowledge encoded in language models. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Houcheng+Jiang%2C+Junfeng+Fang%2C+Ningyu+Zhang%2C+Mingyang+Wan%2C+Guojun+Ma%2C+Xiang+Wang%2C+Xiangnan+He%2C+and+Tat%2DSeng+Chua%2E+2025%2E+Anyedit%3A+Edit+any+knowledge+encoded+in+language+models%2E+In+Forty%2Dsecond+Internati)
11. Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. [Zero-shot relation extraction via reading comprehension](https://md.research.elamur.ai/free/en/papers/levy-2017-zero-shot-relation-extraction-reading/). arXiv preprint arXiv:1706.04115.
12. Jiawei Li, Yang Gao, Yizhe Yang, Yu Bai, Xiaofeng Zhou, Yinghao Li, Huashan Sun, Yuhang Liu, Xingpeng Si, Yuhao Ye, and 1 others. 2025a. Fundamental capabilities and applications of [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). ACM Computing Surveys.
13. Xiaopeng Li, Shasha Li, Shezheng Song, Jing Yang, Jun Ma, and Jie Yu. 2024. [Pmet: Precise model editing in a transformer](https://md.research.elamur.ai/free/en/papers/li-2023-pmet-precise-model-editing-transformer/). In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18564–18572.
14. Zherui Li, Houcheng Jiang, Hao Chen, Baolong Bi, Zhenhong Zhou, Fei Sun, Junfeng Fang, and Xiang Wang. 2025b. Reinforced lifelong editing for language models. arXiv preprint arXiv:2502.05759. — [arXiv:2502.05759](https://arxiv.org/abs/2502.05759) [find](https://scholar.google.com/scholar?q=Zherui+Li%2C+Houcheng+Jiang%2C+Hao+Chen%2C+Baolong+Bi%2C+Zhenhong+Zhou%2C+Fei+Sun%2C+Junfeng+Fang%2C+and+Xiang+Wang%2E+2025b%2E+Reinforced+lifelong+editing+for+language+models%2E+arXiv+preprint+arXiv%3A2502%2E05759%2E+%E2%80%94+%5BarXiv)
15. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. [Truthfulqa: Measuring how models mimic human falsehoods](https://md.research.elamur.ai/free/en/papers/lin-2022-truthfulqa-measuring-how-models-mimic/). In Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: long papers), pages 3214–3252.
16. Xiong Luo, Xiaohui Chang, and Xiaojuan Ban. 2016. Regression and classification using extreme learning machine based on l1-norm and l2-norm. Neurocomputing, 174:179–186. [find](https://scholar.google.com/scholar?q=Xiong+Luo%2C+Xiaohui+Chang%2C+and+Xiaojuan+Ban%2E+2016%2E+Regression+and+classification+using+extreme+learning+machine+based+on+l1%2Dnorm+and+l2%2Dnorm%2E+Neurocomputing%2C+174%3A179%E2%80%93186%2E)
17. Jun-Yu Ma, Hong Wang, Hao-Xiang Xu, Zhen-Hua Ling, and Jia-Chen Gu. 2024. Perturbation-restrained sequential model editing. arXiv preprint arXiv:2405.16821. — [arXiv:2405.16821](https://arxiv.org/abs/2405.16821) [find](https://scholar.google.com/scholar?q=Jun%2DYu+Ma%2C+Hong+Wang%2C+Hao%2DXiang+Xu%2C+Zhen%2DHua+Ling%2C+and+Jia%2DChen+Gu%2E+2024%2E+Perturbation%2Drestrained+sequential+model+editing%2E+arXiv+preprint+arXiv%3A2405%2E16821%2E+%E2%80%94+%5BarXiv%3A2405%2E16821%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F)
18. Aman Madaan, Niket Tandon, Peter Clark, and Yiming Yang. 2022. Memory-assisted prompt editing to improve gpt-3 after deployment. arXiv preprint arXiv:2201.06009. [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Peter+Clark%2C+and+Yiming+Yang%2E+2022%2E+Memory%2Dassisted+prompt+editing+to+improve+gpt%2D3+after+deployment%2E+arXiv+preprint+arXiv%3A2201%2E06009%2E)
19. James L McClelland, Bruce L McNaughton, and Randall C O’Reilly. 1995. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological review, 102(3):419. [find](https://scholar.google.com/scholar?q=James+L+McClelland%2C+Bruce+L+McNaughton%2C+and+Randall+C+O%E2%80%99Reilly%2E+1995%2E+Why+there+are+complementary+learning+systems+in+the+hippocampus+and+neocortex%3A+insights+from+the+successes+and+failures+of+connect)
20. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022a. Locating and editing factual associations in gpt. Advances in neural information processing systems, 35:17359–17372. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+David+Bau%2C+Alex+Andonian%2C+and+Yonatan+Belinkov%2E+2022a%2E+Locating+and+editing+factual+associations+in+gpt%2E+Advances+in+neural+information+processing+systems%2C+35%3A17359%E2%80%9317372%2E)
21. Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, and David Bau. 2022b. Mass-editing memory in a transformer. arXiv preprint arXiv:2210.07229. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+Arnab+Sen+Sharma%2C+Alex+Andonian%2C+Yonatan+Belinkov%2C+and+David+Bau%2E+2022b%2E+Mass%2Dediting+memory+in+a+transformer%2E+arXiv+preprint+arXiv%3A2210%2E07229%2E)
22. Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D Manning. 2021. Fast model editing at scale. arXiv preprint arXiv:2110.11309. [find](https://scholar.google.com/scholar?q=Eric+Mitchell%2C+Charles+Lin%2C+Antoine+Bosselut%2C+Chelsea+Finn%2C+and+Christopher+D+Manning%2E+2021%2E+Fast+model+editing+at+scale%2E+arXiv+preprint+arXiv%3A2110%2E11309%2E)
23. Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D Manning, and Chelsea Finn. 2022. Memory-based model editing at scale. In International Conference on Machine Learning, pages 15817–15831. PMLR. [find](https://scholar.google.com/scholar?q=Eric+Mitchell%2C+Charles+Lin%2C+Antoine+Bosselut%2C+Christopher+D+Manning%2C+and+Chelsea+Finn%2E+2022%2E+Memory%2Dbased+model+editing+at+scale%2E+In+International+Conference+on+Machine+Learning%2C+pages+15817%E2%80%9315831%2E+PM)
24. Laura Ruis, Maximilian Mozes, Juhan Bae, Siddhartha Rao Kamalakara, Dwarak Talupuru, Acyr Locatelli, Robert Kirk, Tim Rocktäschel, Edward Grefenstette, and Max Bartolo. 2024. Procedural knowledge in pretraining drives reasoning in large language models. arXiv preprint arXiv:2411.12580. [find](https://scholar.google.com/scholar?q=Laura+Ruis%2C+Maximilian+Mozes%2C+Juhan+Bae%2C+Siddhartha+Rao+Kamalakara%2C+Dwarak+Talupuru%2C+Acyr+Locatelli%2C+Robert+Kirk%2C+Tim+Rockt%C3%A4schel%2C+Edward+Grefenstette%2C+and+Max+Bartolo%2E+2024%2E+Procedural+knowledge+in+p)
25. Alireza Salemi, Sheshera Mysore, Michael Bendersky, and Hamed Zamani. 2024. [Lamp: When large language models meet personalization](https://md.research.elamur.ai/free/en/papers/salemi-2024-lamp-when-large-language-models/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7370–7392.
26. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2019. [Commonsenseqa: A question answering challenge targeting commonsense knowledge](https://md.research.elamur.ai/free/en/papers/talmor-2019-commonsenseqa-question-answering-challenge-targeting/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
27. Chenmien Tan, Ge Zhang, and Jie Fu. 2023. Massive editing for large language models via meta learning. arXiv preprint arXiv:2311.04661. — [arXiv:2311.04661](https://arxiv.org/abs/2311.04661) [find](https://scholar.google.com/scholar?q=Chenmien+Tan%2C+Ge+Zhang%2C+and+Jie+Fu%2E+2023%2E+Massive+editing+for+large+language+models+via+meta+learning%2E+arXiv+preprint+arXiv%3A2311%2E04661%2E+%E2%80%94+%5BarXiv%3A2311%2E04661%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2311%2E04661%29)
28. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, and 1 others. 2024. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:2408.00118. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Morgane+Riviere%2C+Shreya+Pathak%2C+Pier+Giuseppe+Sessa%2C+Cassidy+Hardin%2C+Surya+Bhupatiraju%2C+L%C3%A9onard+Hussenot%2C+Thomas+Mesnard%2C+Bobak+Shahriari%2C+Alexandre+Ram%C3%A9%2C+and+1+others%2E+2024%2E+Gemma+2%3A+Impr)
29. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. [Fever: a large-scale dataset for fact extraction and verification](https://md.research.elamur.ai/free/en/papers/thorne-2018-fever-large-scale-dataset-fact/). arXiv preprint arXiv:1803.05355.
30. Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, and 1 others. 2022. Benchmarking generalization via in-context instructions on 1,600+ language tasks. arXiv preprint arXiv:2204.07… [find](https://scholar.google.com/scholar?q=Yizhong+Wang%2C+Swaroop+Mishra%2C+Pegah+Alipoormolabashi%2C+Yeganeh+Kordi%2C+Amirreza+Mirzaei%2C+Anjana+Arunkumar%2C+Arjun+Ashok%2C+Arut+Selvan+Dhanasekaran%2C+Atharva+Naik%2C+David+Stap%2C+and+1+others%2E+2022%2E+Benchmarki)
31. Haoyu Xu, Pengxiang Lan, Enneng Yang, Guibing Guo, Jianzhe Zhao, Linying Jiang, and Xingwei Wang. 2025. Knowledge decoupling via orthogonal projection for lifelong editing of large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1:… [find](https://scholar.google.com/scholar?q=Haoyu+Xu%2C+Pengxiang+Lan%2C+Enneng+Yang%2C+Guibing+Guo%2C+Jianzhe+Zhao%2C+Linying+Jiang%2C+and+Xingwei+Wang%2E+2025%2E+Knowledge+decoupling+via+orthogonal+projection+for+lifelong+editing+of+large+language+models%2E+In)
32. Lang Yu, Qin Chen, Jie Zhou, and Liang He. 2024. Melo: Enhancing model editing with neuron-indexed dynamic lora. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19449–19457. [find](https://scholar.google.com/scholar?q=Lang+Yu%2C+Qin+Chen%2C+Jie+Zhou%2C+and+Liang+He%2E+2024%2E+Melo%3A+Enhancing+model+editing+with+neuron%2Dindexed+dynamic+lora%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+38%2C+pages+1944)
33. Taolin Zhang, Qizhou Chen, Dongyang Li, Chengyu Wang, Xiaofeng He, Longtao Huang, Jun Huang, and 1 others. 2024. Dafnet: Dynamic auxiliary fusion for sequential model editing in large language models. In Findings of the Association for Computational Linguistics ACL 2024, pages 1588–1602. [find](https://scholar.google.com/scholar?q=Taolin+Zhang%2C+Qizhou+Chen%2C+Dongyang+Li%2C+Chengyu+Wang%2C+Xiaofeng+He%2C+Longtao+Huang%2C+Jun+Huang%2C+and+1+others%2E+2024%2E+Dafnet%3A+Dynamic+auxiliary+fusion+for+sequential+model+editing+in+large+language+models%2E)
34. Ce Zheng, Lei Li, Qingxiu Dong, Yuxuan Fan, Zhiyong Wu, Jingjing Xu, and Baobao Chang. 2023. Can we edit factual knowledge by in-context learning? arXiv preprint arXiv:2305.12740. [find](https://scholar.google.com/scholar?q=Ce+Zheng%2C+Lei+Li%2C+Qingxiu+Dong%2C+Yuxuan+Fan%2C+Zhiyong+Wu%2C+Jingjing+Xu%2C+and+Baobao+Chang%2E+2023%2E+Can+we+edit+factual+knowledge+by+in%2Dcontext+learning%3F+arXiv+preprint+arXiv%3A2305%2E12740%2E)
35. Zexuan Zhong, Zhengxuan Wu, Christopher D Manning, Christopher Potts, and Danqi Chen. 2023. Mquake: Assessing knowledge editing in language models via multi-hop questions. arXiv preprint arXiv:2305.14795. [find](https://scholar.google.com/scholar?q=Zexuan+Zhong%2C+Zhengxuan+Wu%2C+Christopher+D+Manning%2C+Christopher+Potts%2C+and+Danqi+Chen%2E+2023%2E+Mquake%3A+Assessing+knowledge+editing+in+language+models+via+multi%2Dhop+questions%2E+arXiv+preprint+arXiv%3A2305%2E14)
36. Chen Zhu, Ankit Singh Rawat, Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix Yu, and Sanjiv Kumar. 2020. Modifying memories in transformer models. arXiv preprint arXiv:2012.00363. [find](https://scholar.google.com/scholar?q=Chen+Zhu%2C+Ankit+Singh+Rawat%2C+Manzil+Zaheer%2C+Srinadh+Bhojanapalli%2C+Daliang+Li%2C+Felix+Yu%2C+and+Sanjiv+Kumar%2E+2020%2E+Modifying+memories+in+transformer+models%2E+arXiv+preprint+arXiv%3A2012%2E00363%2E)

*Updated 2 November 2026*