---
title: "HiEdit — paper by Wang et al. (2026) — summary and ideas"
description: "The authors argue that current editors make a mistake by modifying the same fixed, dense block of layers for every fact, even… 37 references."
authors: ["Yangfan Wang", "Tianyang Sun", "Chen Tang", "Jie Liu", "Wei Cai", "Jingchi Jiang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1855/"
doi: "10.18653/v1/2026.acl-long.1855"
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/wang-2026-hiedit-lifelong-model-editing-hierarchical/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-hiedit-lifelong-model-editing-hierarchical/)

[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/32/) / HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning

# HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning

**Authors:** Yangfan Wang, Tianyang Sun, [Chen Tang](https://md.research.elamur.ai/free/en/authors/chen-tang/), [Jie Liu](https://md.research.elamur.ai/free/en/authors/jie-liu/), [Wei Cai](https://md.research.elamur.ai/free/en/authors/wei-cai/) and Jingchi Jiang · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1855/) · [PDF](https://aclanthology.org/2026.acl-long.1855.pdf) · [DOI 10.18653/v1/2026.acl-long.1855](https://doi.org/10.18653/v1/2026.acl-long.1855) · [OpenAlex](https://openalex.org/W7166880156)

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

## Summary
Lifelong model editing (LME) repeatedly corrects outdated or wrong facts in a deployed LLM while trying not to damage unrelated or earlier-edited knowledge. The authors argue that current editors make a mistake by modifying the same fixed, dense block of layers for every fact, even though different facts seem to reside in different layers. This leads to over-modification and catastrophic forgetting. HiEdit casts editing as a two-level hierarchical reinforcement learning problem. A high-level hypernetwork acts as a manager: it reads gradient signals and produces an importance distribution over layers, choosing where to edit. A low-level hypernetwork acts as a worker and computes the actual parameter updates for the chosen layers. An intrinsic reward compares sparse updates against full-layer updates, which pushes the system toward minimal changes. On ZsRE and CounterFact with several LLMs, HiEdit beats RLEdit by 8.48% on average while touching only half the layers per edit. It stays robust over very long edit streams, which matters for keeping deployed models current without retraining.

## Key points
- Stream length: experiments include up to 20,000 sequential ZsRE edits on Llama-3-8B. AlphaEdit degrades markedly by about 8,000 edits. HiEdit keeps General Retention (mean F1 over six GLUE tasks) close to the unedited model.
- Layer selection: layers are chosen with a TopK router, and K is a fixed hyperparameter. Dynamic schemes such as Top-p are left for future work.
- Comparison with random layer choice (Table 3, ZsRE, Llama-3-8B):
  - HiEdit reaches Specificity 48.42 and Retention 75.16.
  - The Random 1 and Random 2 baselines reach Specificity 30.32 and 33.60, and Retention 69.72 and 68.03.
- Learned layer preferences:
  - Across 2,000 samples, layer 13 is selected in over 88% of cases.
  - Music facts tend to use layers 20 and 24.
  - Disease facts tend to use layers 14 and 15.
- Code is available at github.com/yangfanww/hiedit. Evaluation covers only structured general-domain knowledge (ZsRE, CounterFact).

*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

- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 158 works · 28,841 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

## Cite

Cite as: Yangfan Wang, Tianyang Sun, Chen Tang, Jie Liu, Wei Cai and Jingchi Jiang. 2026. HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{wang2026hiedit,
  title = {{HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning}},
  author = {Yangfan Wang, Tianyang Sun, Chen Tang, Jie Liu, Wei Cai and Jingchi Jiang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1855},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1855}
}
```

- [← previous Hidden Sentiments: The Impact of Low-level Adversarial Perturbations on Arabic Sentiment Analysis Services](https://md.research.elamur.ai/free/en/papers/abdelkader-2026-hidden-sentiments-impact-low-level/)
- [next → Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech](https://md.research.elamur.ai/free/en/papers/ouyang-2026-hierarchical-policy-optimization-simultaneous-translation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/)

## References

37 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Pierre-Luc Bacon, Jean Harb, and Doina Precup. 2017. The option-critic architecture. In AAAI 2017. [find](https://scholar.google.com/scholar?q=Pierre%2DLuc+Bacon%2C+Jean+Harb%2C+and+Doina+Precup%2E+2017%2E+The+option%2Dcritic+architecture%2E+In+AAAI+2017%2E)
2. Yoshua Bengio, Nicholas Léonard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432. [find](https://scholar.google.com/scholar?q=Yoshua+Bengio%2C+Nicholas+L%C3%A9onard%2C+and+Aaron+Courville%2E+2013%2E+Estimating+or+propagating+gradients+through+stochastic+neurons+for+conditional+computation%2E+arXiv+preprint+arXiv%3A1308%2E3432%2E)
3. Luisa Bentivogli, Peter Clark, Ido Dagan, and Danilo Giampiccolo. 2009. The fifth pascal recognizing textual entailment challenge. [find](https://scholar.google.com/scholar?q=Luisa+Bentivogli%2C+Peter+Clark%2C+Ido+Dagan%2C+and+Danilo+Giampiccolo%2E+2009%2E+The+fifth+pascal+recognizing+textual+entailment+challenge%2E)
4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/).
5. Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Shi Jie, Xiang Wang, Xiangnan He, and Tat-Seng Chua. 2025. Alphaedit: Null-space constrained knowledge editing for language models. [find](https://scholar.google.com/scholar?q=Junfeng+Fang%2C+Houcheng+Jiang%2C+Kun+Wang%2C+Yunshan+Ma%2C+Shi+Jie%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)
6. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
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/). In EMNLP 2024.
8. Jean Harb, Pierre-Luc Bacon, Martin Klissarov, and Doina Precup. 2018. When waiting is not an option: Learning options with a deliberation cost. In AAAI 2018. [find](https://scholar.google.com/scholar?q=Jean+Harb%2C+Pierre%2DLuc+Bacon%2C+Martin+Klissarov%2C+and+Doina+Precup%2E+2018%2E+When+waiting+is+not+an+option%3A+Learning+options+with+a+deliberation+cost%2E+In+AAAI+2018%2E)
9. Tom Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim, and Marzyeh Ghassemi. 2023. Aging with grace: Lifelong model editing with discrete key-value adaptors. [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)
10. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). In ICLR 2021.
11. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. [LoRA: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/).
12. Jingchi Jiang, Rujia Shen, Chao Zhao, Yi Guan, Xuehui Yu, and Xuelian Fu. 2025. Causal discovery based on hierarchical reinforcement learning. Expert Systems with Applications 2025. [find](https://scholar.google.com/scholar?q=Jingchi+Jiang%2C+Rujia+Shen%2C+Chao+Zhao%2C+Yi+Guan%2C+Xuehui+Yu%2C+and+Xuelian+Fu%2E+2025%2E+Causal+discovery+based+on+hierarchical+reinforcement+learning%2E+Expert+Systems+with+Applications+2025%2E)
13. Angeliki Lazaridou, Adhi Kuncoro, Elena Gribovskaya, Devang Agrawal, Adam Liska, Tayfun Terzi, Mai Gimenez, Cyprien de Masson d’Autume, Tomas Kocisky, Sebastian Ruder, and 1 others. 2021. Mind the gap: Assessing temporal generalization in neural language models. [find](https://scholar.google.com/scholar?q=Angeliki+Lazaridou%2C+Adhi+Kuncoro%2C+Elena+Gribovskaya%2C+Devang+Agrawal%2C+Adam+Liska%2C+Tayfun+Terzi%2C+Mai+Gimenez%2C+Cyprien+de+Masson+d%E2%80%99Autume%2C+Tomas+Kocisky%2C+Sebastian+Ruder%2C+and+1+others%2E+2021%2E+Mind+the+gap)
14. 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/). In CoNLL 2017.
15. Zherui Li, Houcheng Jiang, Hao Chen, Baolong Bi, Zhenhong Zhou, Fei Sun, Junfeng Fang, and Xiang Wang. 2025. Reinforced lifelong editing for language models. [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+2025%2E+Reinforced+lifelong+editing+for+language+models%2E)
16. Nicola De Cao, Wilker Aziz, and Ivan Titov. 2021. Editing factual knowledge in language models. In EMNLP 2021. [find](https://scholar.google.com/scholar?q=Nicola+De+Cao%2C+Wilker+Aziz%2C+and+Ivan+Titov%2E+2021%2E+Editing+factual+knowledge+in+language+models%2E+In+EMNLP+2021%2E)
17. Jun-Yu Ma, Hong Wang, Hao-Xiang Xu, Zhen-Hua Ling, and Jia-Chen Gu. 2024. Perturbation-restrained sequential model editing. [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)
18. William B Dolan and Chris Brockett. 2005. [Automatically constructing a corpus of sentential paraphrases](https://md.research.elamur.ai/free/en/papers/dolan-2005-automatically-constructing-corpus-sentential-paraphrases/). In IWP 2005.
19. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in gpt. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+David+Bau%2C+Alex+Andonian%2C+and+Yonatan+Belinkov%2E+2022%2E+Locating+and+editing+factual+associations+in+gpt%2E)
20. Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, and David Bau. 2023. Mass-editing memory in a transformer. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+Arnab+Sen+Sharma%2C+Alex+Andonian%2C+Yonatan+Belinkov%2C+and+David+Bau%2E+2023%2E+Mass%2Dediting+memory+in+a+transformer%2E)
21. Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D Manning. 2022. Fast model editing at scale. [find](https://scholar.google.com/scholar?q=Eric+Mitchell%2C+Charles+Lin%2C+Antoine+Bosselut%2C+Chelsea+Finn%2C+and+Christopher+D+Manning%2E+2022%2E+Fast+model+editing+at+scale%2E)
22. Ofir Nachum, Shixiang Shane Gu, Honglak Lee, and Sergey Levine. 2018. Data-efficient hierarchical reinforcement learning. [find](https://scholar.google.com/scholar?q=Ofir+Nachum%2C+Shixiang+Shane+Gu%2C+Honglak+Lee%2C+and+Sergey+Levine%2E+2018%2E+Data%2Defficient+hierarchical+reinforcement+learning%2E)
23. Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander Miller. 2019. [Language models as knowledge bases?](https://md.research.elamur.ai/free/en/papers/petroni-2019-language-models-as-knowledge-bases/) In EMNLP 2019.
24. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, and Christopher Potts. 2013. [Recursive deep models for semantic compositionality over a sentiment treebank](https://md.research.elamur.ai/free/en/papers/socher-2013-recursive-deep-models-semantic-compositionality/). In EMNLP 2013.
25. Richard S Sutton, Doina Precup, and Satinder Singh. 1999. Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial intelligence 1999. [find](https://scholar.google.com/scholar?q=Richard+S+Sutton%2C+Doina+Precup%2C+and+Satinder+Singh%2E+1999%2E+Between+mdps+and+semi%2Dmdps%3A+A+framework+for+temporal+abstraction+in+reinforcement+learning%2E+Artificial+intelligence+1999%2E)
26. Chenmien Tan, Ge Zhang, and Jie Fu. 2024. Massive editing for large language models via meta learning. [find](https://scholar.google.com/scholar?q=Chenmien+Tan%2C+Ge+Zhang%2C+and+Jie+Fu%2E+2024%2E+Massive+editing+for+large+language+models+via+meta+learning%2E)
27. Chen Tang, Bo Lv, Zifan Zheng, Bohao Yang, Kun Zhao, Ning Liao, Xiaoxing Wang, Feiyu Xiong, Zhiyu Li, Nayu Liu, and 1 others. 2025. Graphmoe: Amplifying cognitive depth of mixture-of-experts network via introducing self-rethinking mechanism. arXiv preprint arXiv:2501.07890. — [arXiv:2501.07890](https://arxiv.org/abs/2501.07890) [find](https://scholar.google.com/scholar?q=Chen+Tang%2C+Bo+Lv%2C+Zifan+Zheng%2C+Bohao+Yang%2C+Kun+Zhao%2C+Ning+Liao%2C+Xiaoxing+Wang%2C+Feiyu+Xiong%2C+Zhiyu+Li%2C+Nayu+Liu%2C+and+1+others%2E+2025%2E+Graphmoe%3A+Amplifying+cognitive+depth+of+mixture%2Dof%2Dexperts+network+v)
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. Chen Tessler, Shahar Givony, Tom Zahavy, Daniel Mankowitz, and Shie Mannor. 2017. A deep hierarchical approach to lifelong learning in minecraft. In AAAI 2017. [find](https://scholar.google.com/scholar?q=Chen+Tessler%2C+Shahar+Givony%2C+Tom+Zahavy%2C+Daniel+Mankowitz%2C+and+Shie+Mannor%2E+2017%2E+A+deep+hierarchical+approach+to+lifelong+learning+in+minecraft%2E+In+AAAI+2017%2E)
30. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. [Glue: A multi-task benchmark and analysis platform for natural language understanding](https://md.research.elamur.ai/free/en/papers/wang-2018-glue-multi-task-benchmark-analysis/). In Workshop BlackboxNLP of EMNLP 2018.
31. Haoyu Wang, Tianci Liu, Ruirui Li, Monica Xiao Cheng, Tuo Zhao, and Jing Gao. 2024. Roselora: Row and column-wise sparse low-rank adaptation of pre-trained language model for knowledge editing and fine-tuning. In EMNLP 2024. [find](https://scholar.google.com/scholar?q=Haoyu+Wang%2C+Tianci+Liu%2C+Ruirui+Li%2C+Monica+Xiao+Cheng%2C+Tuo+Zhao%2C+and+Jing+Gao%2E+2024%2E+Roselora%3A+Row+and+column%2Dwise+sparse+low%2Drank+adaptation+of+pre%2Dtrained+language+model+for+knowledge+editing+and+fin)
32. Alex Warstadt, Amanpreet Singh, and Samuel R Bowman. 2019. Neural network acceptability judgments. [find](https://scholar.google.com/scholar?q=Alex+Warstadt%2C+Amanpreet+Singh%2C+and+Samuel+R+Bowman%2E+2019%2E+Neural+network+acceptability+judgments%2E)
33. Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. [A broad-coverage challenge corpus for sentence understanding through inference](https://md.research.elamur.ai/free/en/papers/williams-2018-broad-coverage-challenge-corpus-sentence/). In NAACL 2018.
34. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, and 1 others. 2020. [Transformers: State-of-the-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). In EMNLP 2020.
35. Yunzhi Yao, Ningyu Zhang, Zekun Xi, Mengru Wang, Ziwen Xu, Shumin Deng, and Huajun Chen. 2024. Knowledge circuits in pretrained transformers. [find](https://scholar.google.com/scholar?q=Yunzhi+Yao%2C+Ningyu+Zhang%2C+Zekun+Xi%2C+Mengru+Wang%2C+Ziwen+Xu%2C+Shumin+Deng%2C+and+Huajun+Chen%2E+2024%2E+Knowledge+circuits+in+pretrained+transformers%2E)
36. 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 ACL 2024. [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)
37. 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 1 November 2026*