---
title: "LOKA — paper by Zhang et al. (2026) — summary and ideas"
description: "LLMs need regular refreshing as facts change and as harmful or sensitive content is discovered. 94 references."
authors: ["Binchi Zhang", "Zhengzhang Chen", "Zaiyi Zheng", "Jundong Li", "Haifeng Chen"]
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.760/"
doi: "10.18653/v1/2026.acl-long.760"
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/zhang-2026-loka-conflict-aware-llm-knowledge/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-loka-conflict-aware-llm-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/40/) / LOKA: Conflict-Aware LLM Knowledge Update with Adaptive Knowledge Memory

# LOKA: Conflict-Aware LLM Knowledge Update with Adaptive Knowledge Memory

**Authors:** [Binchi Zhang](https://md.research.elamur.ai/free/en/authors/binchi-zhang/), [Zhengzhang Chen](https://md.research.elamur.ai/free/en/authors/zhengzhang-chen/), Zaiyi Zheng, [Jundong Li](https://md.research.elamur.ai/free/en/authors/jundong-li/) and [Haifeng Chen](https://md.research.elamur.ai/free/en/authors/haifeng-chen/) · **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.760/) · [PDF](https://aclanthology.org/2026.acl-long.760.pdf) · [DOI 10.18653/v1/2026.acl-long.760](https://doi.org/10.18653/v1/2026.acl-long.760) · [OpenAlex](https://openalex.org/W7166889754)

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

## Summary
LLMs need regular refreshing as facts change and as harmful or sensitive content is discovered. This means adding new knowledge and erasing old knowledge in the same update. The authors identify two obstacles. First, the gradients of learning and unlearning objectives often point in opposite directions. Second, existing external-memory methods either spread knowledge over many memories, which causes overfitting, or pack it into a single memory, which causes underfitting.

LOKA keeps the base LLM frozen and stores updates in an adaptive knowledge memory made of several units attached at a target FFN layer. Its main components work as follows:
- **Conflict handling:** a conflict score based on task similarity sends strongly conflicting items to task-specific units and mildly conflicting ones to multi-task units.
- **Knowledge mapping:** similarity-aware mapping groups related items into the same unit.
- **Routing:** a learned router decides at inference whether memory is needed and, if so, retrieves the most relevant unit.

On three real-world datasets, including TOFU, LOKA produces accurate, flexible updates and stays robust under sequential requests. The work treats model weights as read-write memory for keeping deployed models current and safe.

## Key points
- **Conflict evidence:** a pilot study on TOFU used LLM surgery for one epoch. Learning and unlearning gradients had negative cosine similarity in most mini-batches, roughly 83% and 75% of iterations according to the histogram. Conflict was stronger on the in-profile split, where the two datasets overlap more.
- **Allocation trade-off:** a ROUGE-L comparison illustrates the dilemma. GRACE (sparse allocation) scores best on the learning set but worst on paraphrased questions, showing overfitting. WISE (dense allocation) loses gradient information and underfits.
- **Three update goals:** learn from D_l, unlearn D_u, and preserve D_r. The method updates only external parameters, which avoids catastrophic forgetting in the original model.
- **Limitations:** LOKA depends on two hand-set thresholds (conflict and router confidence) that need domain-specific tuning. Lifelong updating remains open; the authors compare reusing existing units via LSH (constant memory cost) with adding new units via KMeans.
- **Contrast with RAG:** retrieval-augmented memory is read-only and cannot actively forget. LOKA writes, removes, and preserves parametric knowledge without changing the original weights.

*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

- [University of Virginia](https://md.research.elamur.ai/free/en/universities/university-of-virginia/) — University, Charlottesville, United States · 40 works · 10,099 citations
- [NEC (United States)](https://md.research.elamur.ai/free/en/companies/nec/) — Company, Irving, United States · 10 works · 658 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: Binchi Zhang, Zhengzhang Chen, Zaiyi Zheng, Jundong Li and Haifeng Chen. 2026. LOKA: Conflict-Aware LLM Knowledge Update with Adaptive Knowledge Memory. 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{zhang2026loka,
  title = {{LOKA: Conflict-Aware LLM Knowledge Update with Adaptive Knowledge Memory}},
  author = {Binchi Zhang, Zhengzhang Chen, Zaiyi Zheng, Jundong Li and Haifeng Chen},
  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.760},
  url = {https://doi.org/10.18653/v1/2026.acl-long.760}
}
```

- [← previous LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software](https://md.research.elamur.ai/free/en/papers/rashid-2026-logiceval-systematic-framework-evaluating-automated/)
- [next → Long-Term Sign Language Data Crowdsourcing Through Collaborative Lexicons](https://md.research.elamur.ai/free/en/papers/poitier-2026-long-term-sign-language-data/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/40/)

## References

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

1. Lucas Bourtoule, Varun Chandrasekaran, Christopher A Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot. 2021. Machine unlearning. In 2021 IEEE Symposium on Security and Privacy (SP), pages 141–159. [find](https://scholar.google.com/scholar?q=Lucas+Bourtoule%2C+Varun+Chandrasekaran%2C+Christopher+A+Choquette%2DChoo%2C+Hengrui+Jia%2C+Adelin+Travers%2C+Baiwu+Zhang%2C+David+Lie%2C+and+Nicolas+Papernot%2E+2021%2E+Machine+unlearning%2E+In+2021+IEEE+Symposium+on+Secu)
2. 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/). Advances in neural information processing systems, 33:1877–1901.
3. Yinzhi Cao and Junfeng Yang. 2015. Towards making systems forget with machine unlearning. In 2015 IEEE symposium on security and privacy, pages 463– 480. [find](https://scholar.google.com/scholar?q=Yinzhi+Cao+and+Junfeng+Yang%2E+2015%2E+Towards+making+systems+forget+with+machine+unlearning%2E+In+2015+IEEE+symposium+on+security+and+privacy%2C+pages+463%E2%80%93+480%2E)
4. Valérie Castin, Pierre Ablin, and Gabriel Peyré. 2024. How smooth is attention? In International Conference on Machine Learning, pages 5817–5840. [find](https://scholar.google.com/scholar?q=Val%C3%A9rie+Castin%2C+Pierre+Ablin%2C+and+Gabriel+Peyr%C3%A9%2E+2024%2E+How+smooth+is+attention%3F+In+International+Conference+on+Machine+Learning%2C+pages+5817%E2%80%935840%2E)
5. Heyan Chai, Zeyu Liu, Yongxin Tong, Ziyi Yao, Binxing Fang, and Qing Liao. 2024. Towards task-conflicts momentum-calibrated approach for multi-task learning. In 2024 IEEE 40th International Conference on Data Engineering (ICDE), pages 939– 952. [find](https://scholar.google.com/scholar?q=Heyan+Chai%2C+Zeyu+Liu%2C+Yongxin+Tong%2C+Ziyi+Yao%2C+Binxing+Fang%2C+and+Qing+Liao%2E+2024%2E+Towards+task%2Dconflicts+momentum%2Dcalibrated+approach+for+multi%2Dtask+learning%2E+In+2024+IEEE+40th+International+Conference)
6. Hoyeon Chang, Jinho Park, Seonghyeon Ye, Sohee Yang, Youngkyung Seo, Du-Seong Chang, and Minjoon Seo. 2024. How do large language models acquire factual knowledge during pretraining? Advances in Neural Information Processing Systems, 37. [find](https://scholar.google.com/scholar?q=Hoyeon+Chang%2C+Jinho+Park%2C+Seonghyeon+Ye%2C+Sohee+Yang%2C+Youngkyung+Seo%2C+Du%2DSeong+Chang%2C+and+Minjoon+Seo%2E+2024%2E+How+do+large+language+models+acquire+factual+knowledge+during+pretraining%3F+Advances+in+Neura)
7. Moses S Charikar. 2002. [Similarity estimation techniques from rounding algorithms](https://md.research.elamur.ai/free/en/papers/charikar-2002-similarity-estimation-techniques-rounding/). In Proceedings of the thiry-fourth annual ACM symposium on Theory of computing, pages 380–388.
8. Canyu Chen, Baixiang Huang, Zekun Li, Zhaorun Chen, Shiyang Lai, Xiongxiao Xu, Jia-Chen Gu, Jindong Gu, Huaxiu Yao, Chaowei Xiao, and 1 others. 2024. Can editing llms inject harm? arXiv preprint arXiv:2407.20224. — [arXiv:2407.20224](https://arxiv.org/abs/2407.20224) [find](https://scholar.google.com/scholar?q=Canyu+Chen%2C+Baixiang+Huang%2C+Zekun+Li%2C+Zhaorun+Chen%2C+Shiyang+Lai%2C+Xiongxiao+Xu%2C+Jia%2DChen+Gu%2C+Jindong+Gu%2C+Huaxiu+Yao%2C+Chaowei+Xiao%2C+and+1+others%2E+2024%2E+Can+editing+llms+inject+harm%3F+arXiv+preprint+arXiv)
9. Jiaao Chen and Diyi Yang. 2023. [Unlearn what you want to forget: Efficient unlearning for llms](https://md.research.elamur.ai/free/en/papers/chen-2023-unlearn-what-you-want-forget/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12041– 12052.
10. Sanyuan Chen, Yutai Hou, Yiming Cui, Wanxiang Che, Ting Liu, and Xiangzhan Yu. 2020a. Recall and learn: Fine-tuning deep pretrained language models with less forgetting. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7870–7881. [find](https://scholar.google.com/scholar?q=Sanyuan+Chen%2C+Yutai+Hou%2C+Yiming+Cui%2C+Wanxiang+Che%2C+Ting+Liu%2C+and+Xiangzhan+Yu%2E+2020a%2E+Recall+and+learn%3A+Fine%2Dtuning+deep+pretrained+language+models+with+less+forgetting%2E+In+Proceedings+of+the+2020+Con)
11. Ronen Eldan and Mark Russinovich. 2023. [Who’s harry potter?](https://md.research.elamur.ai/free/en/papers/eldan-2023-who-s-harry-potter-approximate/) approximate unlearning in llms. arXiv preprint arXiv:2310.02238.
12. Zhao Chen, Jiquan Ngiam, Yanping Huang, Thang Luong, Henrik Kretzschmar, Yuning Chai, and Dragomir Anguelov. 2020b. Just pick a sign: Optimizing deep multitask models with gradient sign dropout. Advances in Neural Information Processing Systems, 33:2039–2050. [find](https://scholar.google.com/scholar?q=Zhao+Chen%2C+Jiquan+Ngiam%2C+Yanping+Huang%2C+Thang+Luong%2C+Henrik+Kretzschmar%2C+Yuning+Chai%2C+and+Dragomir+Anguelov%2E+2020b%2E+Just+pick+a+sign%3A+Optimizing+deep+multitask+models+with+gradient+sign+dropout%2E+Advan)
13. Mahyar Fazlyab, Alexander Robey, Hamed Hassani, Manfred Morari, and George Pappas. 2019. Efficient and accurate estimation of lipschitz constants for deep neural networks. Advances in neural information processing systems, 32. [find](https://scholar.google.com/scholar?q=Mahyar+Fazlyab%2C+Alexander+Robey%2C+Hamed+Hassani%2C+Manfred+Morari%2C+and+George+Pappas%2E+2019%2E+Efficient+and+accurate+estimation+of+lipschitz+constants+for+deep+neural+networks%2E+Advances+in+neural+informati)
14. Siyuan Cheng, Ningyu Zhang, Bozhong Tian, Xi Chen, Qingbin Liu, and Huajun Chen. 2024. Editing language model-based knowledge graph embeddings. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 17835–17843. [find](https://scholar.google.com/scholar?q=Siyuan+Cheng%2C+Ningyu+Zhang%2C+Bozhong+Tian%2C+Xi+Chen%2C+Qingbin+Liu%2C+and+Huajun+Chen%2E+2024%2E+Editing+language+model%2Dbased+knowledge+graph+embeddings%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Inte)
15. Kyunghyun Cho, Bart van Merriënboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. [On the properties of neural machine translation: Encoder–decoder approaches](https://md.research.elamur.ai/free/en/papers/cho-2014-properties-neural-machine-translation-encoder/). In Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pages 103–111.
16. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, and 1 others. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168.
17. Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, and Furu Wei. 2022. Knowledge neurons in pretrained transformers. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8493– 8502. [find](https://scholar.google.com/scholar?q=Damai+Dai%2C+Li+Dong%2C+Yaru+Hao%2C+Zhifang+Sui%2C+Baobao+Chang%2C+and+Furu+Wei%2E+2022%2E+Knowledge+neurons+in+pretrained+transformers%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computationa)
18. Nicola De Cao, Wilker Aziz, and Ivan Titov. 2021. Editing factual knowledge in language models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6491– 6506. [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+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+6491%E2%80%93+6)
19. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
20. Chris Fifty, Ehsan Amid, Zhe Zhao, Tianhe Yu, Rohan Anil, and Chelsea Finn. 2021. Efficiently identifying task groupings for multi-task learning. Advances in Neural Information Processing Systems, 34:27503– 27516. [find](https://scholar.google.com/scholar?q=Chris+Fifty%2C+Ehsan+Amid%2C+Zhe+Zhao%2C+Tianhe+Yu%2C+Rohan+Anil%2C+and+Chelsea+Finn%2E+2021%2E+Efficiently+identifying+task+groupings+for+multi%2Dtask+learning%2E+Advances+in+Neural+Information+Processing+Systems%2C+34%3A)
21. Joshua Freeman, Chloe Rippe, Edoardo Debenedetti, and Maksym Andriushchenko. 2024. Exploring memorization and copyright violation in frontier llms: A study of the new york times v. openai 2023 lawsuit. arXiv preprint arXiv:2412.06370. — [arXiv:2412.06370](https://arxiv.org/abs/2412.06370) [find](https://scholar.google.com/scholar?q=Joshua+Freeman%2C+Chloe+Rippe%2C+Edoardo+Debenedetti%2C+and+Maksym+Andriushchenko%2E+2024%2E+Exploring+memorization+and+copyright+violation+in+frontier+llms%3A+A+study+of+the+new+york+times+v%2E+openai+2023+lawsuit)
22. Chongyang Gao, Lixu Wang, Chenkai Weng, Xiao Wang, and Qi Zhu. 2024. Practical unlearning for large language models. arXiv preprint arXiv:2407.10223. — [arXiv:2407.10223](https://arxiv.org/abs/2407.10223) [find](https://scholar.google.com/scholar?q=Chongyang+Gao%2C+Lixu+Wang%2C+Chenkai+Weng%2C+Xiao+Wang%2C+and+Qi+Zhu%2E+2024%2E+Practical+unlearning+for+large+language+models%2E+arXiv+preprint+arXiv%3A2407%2E10223%2E+%E2%80%94+%5BarXiv%3A2407%2E10223%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2407%2E10)
23. Chuan Guo, Tom Goldstein, Awni Hannun, and Laurens Van Der Maaten. 2020. Certified data removal from machine learning models. In International Conference on Machine Learning, pages 3832–3842. [find](https://scholar.google.com/scholar?q=Chuan+Guo%2C+Tom+Goldstein%2C+Awni+Hannun%2C+and+Laurens+Van+Der+Maaten%2E+2020%2E+Certified+data+removal+from+machine+learning+models%2E+In+International+Conference+on+Machine+Learning%2C+pages+3832%E2%80%933842%2E)
24. Akshat Gupta, Dev Sajnani, and Gopala Anumanchipalli. 2024. A unified framework for model editing. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 15403– 15418. [find](https://scholar.google.com/scholar?q=Akshat+Gupta%2C+Dev+Sajnani%2C+and+Gopala+Anumanchipalli%2E+2024%2E+A+unified+framework+for+model+editing%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2024%2C+pages+15403%E2%80%93+15418%2E)
25. 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. [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)
26. Xiaochen He, Guanzhao Cheng, and Jiali Lu. 2025. Tag-mediated effect on the dynamics of social influence. PLoS One, 20(12):e0338598. [find](https://scholar.google.com/scholar?q=Xiaochen+He%2C+Guanzhao+Cheng%2C+and+Jiali+Lu%2E+2025%2E+Tag%2Dmediated+effect+on+the+dynamics+of+social+influence%2E+PLoS+One%2C+20%2812%29%3Ae0338598%2E)
27. 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 International Conference on Learning Representations.
28. 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/). In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5937–5947.
29. Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and 1 others. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In International Conference on Learning Representations.
30. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, 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.
31. Xuming Hu, Junzhe Chen, Xiaochuan Li, Yufei Guo, Lijie Wen, S Yu Philip, and Zhijiang Guo. 2024. Towards understanding factual knowledge of large language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Xuming+Hu%2C+Junzhe+Chen%2C+Xiaochuan+Li%2C+Yufei+Guo%2C+Lijie+Wen%2C+S+Yu+Philip%2C+and+Zhijiang+Guo%2E+2024%2E+Towards+understanding+factual+knowledge+of+large+language+models%2E+In+International+Conference+on+Learni)
32. Zeyu Huang, Yikang Shen, Xiaofeng Zhang, Jie Zhou, Wenge Rong, and Zhang Xiong. 2023. [Transformer-patcher: One mistake worth one neuron](https://md.research.elamur.ai/free/en/papers/huang-2023-transformer-patcher-one-mistake-worth/). In International Conference on Learning Representations.
33. Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2023. [Editing models with task arithmetic](https://md.research.elamur.ai/free/en/papers/ilharco-2022-editing-models-task-arithmetic/). In International Conference on Learning Representations.
34. Piotr Indyk and Rajeev Motwani. 1998. Approximate nearest neighbors: towards removing the curse of dimensionality. In Proceedings of the thirtieth annual ACM symposium on Theory of computing, pages 604–613. [find](https://scholar.google.com/scholar?q=Piotr+Indyk+and+Rajeev+Motwani%2E+1998%2E+Approximate+nearest+neighbors%3A+towards+removing+the+curse+of+dimensionality%2E+In+Proceedings+of+the+thirtieth+annual+ACM+symposium+on+Theory+of+computing%2C+pages+60)
35. Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2023. [Atlas: Few-shot learning with retrieval augmented language models](https://md.research.elamur.ai/free/en/papers/izacard-2022-atlas-few-shot-learning-retrieval/). Journal of Machine Learning Research, 24(251):1–43.
36. Jiaming Ji, Mickel Liu, Josef Dai, Xuehai Pan, Chi Zhang, Ce Bian, Boyuan Chen, Ruiyang Sun, Yizhou Wang, and Yaodong Yang. 2023. [Beavertails: Towards improved safety alignment of llm via a human-preference dataset](https://md.research.elamur.ai/free/en/papers/ji-2023-beavertails-towards-improved-safety-alignment/). Advances in Neural Information Processing Systems, 36.
37. Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, and Sijia Liu. 2024. [Soul: Unlocking the power of second-order optimization for llm unlearning](https://md.research.elamur.ai/free/en/papers/jia-2024-soul-unlocking-power-second-order/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages…
38. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, and 1 others. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. [find](https://scholar.google.com/scholar?q=Albert+Q+Jiang%2C+Alexandre+Sablayrolles%2C+Arthur+Mensch%2C+Chris+Bamford%2C+Devendra+Singh+Chaplot%2C+Diego+de+las+Casas%2C+Florian+Bressand%2C+Gianna+Lengyel%2C+Guillaume+Lample%2C+Lucile+Saulnier%2C+and+1+others%2E+202)
39. Hyunjik Kim, George Papamakarios, and Andriy Mnih. 2021. The lipschitz constant of self-attention. In International Conference on Machine Learning, pages 5562–5571. [find](https://scholar.google.com/scholar?q=Hyunjik+Kim%2C+George+Papamakarios%2C+and+Andriy+Mnih%2E+2021%2E+The+lipschitz+constant+of+self%2Dattention%2E+In+International+Conference+on+Machine+Learning%2C+pages+5562%E2%80%935571%2E)
40. Fabian Latorre, Paul Rolland, and Volkan Cevher. 2020. Lipschitz constant estimation of neural networks via sparse polynomial optimization. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Fabian+Latorre%2C+Paul+Rolland%2C+and+Volkan+Cevher%2E+2020%2E+Lipschitz+constant+estimation+of+neural+networks+via+sparse+polynomial+optimization%2E+In+International+Conference+on+Learning+Representations%2E)
41. 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 Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 333–342.
42. Daliang Li, Ankit Singh Rawat, Manzil Zaheer, Xin Wang, Michal Lukasik, Andreas Veit, Felix Yu, and Sanjiv Kumar. 2023. [Large language models with controllable working memory](https://md.research.elamur.ai/free/en/papers/li-2023-large-language-models-controllable-working/). In Findings of the Association for Computational Linguistics: ACL 2023, pages 1774–1793.
43. Xiaopeng Li, Shasha Li, Shezheng Song, Jing Yang, Jun Ma, and Jie Yu. 2024a. [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.
44. Zhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang, Xi Chen, and Huajun Chen. 2024b. Unveiling the pitfalls of knowledge editing for large language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Zhoubo+Li%2C+Ningyu+Zhang%2C+Yunzhi+Yao%2C+Mengru+Wang%2C+Xi+Chen%2C+and+Huajun+Chen%2E+2024b%2E+Unveiling+the+pitfalls+of+knowledge+editing+for+large+language+models%2E+In+International+Conference+on+Learning+Repres)
45. Chin-Yew Lin. 2004. [ROUGE: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text Summarization Branches Out, pages 74–81.
46. Xi Lin, Hui-Ling Zhen, Zhenhua Li, Qing-Fu Zhang, and Sam Kwong. 2019. Pareto multi-task learning. Advances in neural information processing systems, 32. [find](https://scholar.google.com/scholar?q=Xi+Lin%2C+Hui%2DLing+Zhen%2C+Zhenhua+Li%2C+Qing%2DFu+Zhang%2C+and+Sam+Kwong%2E+2019%2E+Pareto+multi%2Dtask+learning%2E+Advances+in+neural+information+processing+systems%2C+32%2E)
47. Bo Liu, Xingchao Liu, Xiaojie Jin, Peter Stone, and Qiang Liu. 2021. Conflict-averse gradient descent for multi-task learning. Advances in Neural Information Processing Systems, 34:18878–18890. [find](https://scholar.google.com/scholar?q=Bo+Liu%2C+Xingchao+Liu%2C+Xiaojie+Jin%2C+Peter+Stone%2C+and+Qiang+Liu%2E+2021%2E+Conflict%2Daverse+gradient+descent+for+multi%2Dtask+learning%2E+Advances+in+Neural+Information+Processing+Systems%2C+34%3A18878%E2%80%9318890%2E)
48. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024a. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the Association for Computational Linguistics, 12.
49. Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Yuguang Yao, Chris Yuhao Liu, Xiaojun Xu, Hang Li, and 1 others. 2024b. Rethinking machine unlearning for large language models. arXiv preprint arXiv:2402.08787. [find](https://scholar.google.com/scholar?q=Sijia+Liu%2C+Yuanshun+Yao%2C+Jinghan+Jia%2C+Stephen+Casper%2C+Nathalie+Baracaldo%2C+Peter+Hase%2C+Yuguang+Yao%2C+Chris+Yuhao+Liu%2C+Xiaojun+Xu%2C+Hang+Li%2C+and+1+others%2E+2024b%2E+Rethinking+machine+unlearning+for+large+la)
50. Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan, Yijun Tian, and Meng Jiang. 2024c. Machine unlearning in generative ai: A survey. arXiv preprint arXiv:2407.20516. — [arXiv:2407.20516](https://arxiv.org/abs/2407.20516) [find](https://scholar.google.com/scholar?q=Zheyuan+Liu%2C+Guangyao+Dou%2C+Zhaoxuan+Tan%2C+Yijun+Tian%2C+and+Meng+Jiang%2E+2024c%2E+Machine+unlearning+in+generative+ai%3A+A+survey%2E+arXiv+preprint+arXiv%3A2407%2E20516%2E+%E2%80%94+%5BarXiv%3A2407%2E20516%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2)
51. Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan, Yijun Tian, and Meng Jiang. 2024d. [Towards safer large language models through machine unlearning](https://md.research.elamur.ai/free/en/papers/liu-2024-safer-large-language-models-through/). In Findings of the Association for Computational Linguistics: ACL 2024.
52. Stuart Lloyd. 1982. Least squares quantization in pcm. IEEE transactions on information theory, 28(2):129– 137. [find](https://scholar.google.com/scholar?q=Stuart+Lloyd%2E+1982%2E+Least+squares+quantization+in+pcm%2E+IEEE+transactions+on+information+theory%2C+28%282%29%3A129%E2%80%93+137%2E)
53. Jiali Lu, Guangyu Li, and Xiaochen He. 2026. Structure, influence, and consensus: Modeling majority-driven dynamics on hypernetworks. Chaos, Solitons & Fractals, 206:117906. [find](https://scholar.google.com/scholar?q=Jiali+Lu%2C+Guangyu+Li%2C+and+Xiaochen+He%2E+2026%2E+Structure%2C+influence%2C+and+consensus%3A+Modeling+majority%2Ddriven+dynamics+on+hypernetworks%2E+Chaos%2C+Solitons+%26+Fractals%2C+206%3A117906%2E)
54. Pratyush Maini, Zhili Feng, Avi Schwarzschild, Zachary Chase Lipton, and J Zico Kolter. 2024. [TOFU: A task of fictitious unlearning for LLMs](https://md.research.elamur.ai/free/en/papers/maini-2024-tofu-task-fictitious-unlearning-llms/). In Conference on Language Modeling.
55. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. 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+2022%2E+Locating+and+editing+factual+associations+in+gpt%2E+Advances+in+Neural+Information+Processing+Systems%2C+35%3A17359%E2%80%9317372%2E)
56. Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2022. [Rethinking the role of demonstrations: What makes in-context learning work?](https://md.research.elamur.ai/free/en/papers/min-2022-rethinking-role-demonstrations-what-makes/) In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11048–11064.
57. Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D Manning. 2022a. Fast model editing at scale. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Eric+Mitchell%2C+Charles+Lin%2C+Antoine+Bosselut%2C+Chelsea+Finn%2C+and+Christopher+D+Manning%2E+2022a%2E+Fast+model+editing+at+scale%2E+In+International+Conference+on+Learning+Representations%2E)
58. Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D Manning, and Chelsea Finn. 2022b. Memory-based model editing at scale. In International Conference on Machine Learning, pages 15817–15831. [find](https://scholar.google.com/scholar?q=Eric+Mitchell%2C+Charles+Lin%2C+Antoine+Bosselut%2C+Christopher+D+Manning%2C+and+Chelsea+Finn%2E+2022b%2E+Memory%2Dbased+model+editing+at+scale%2E+In+International+Conference+on+Machine+Learning%2C+pages+15817%E2%80%9315831%2E)
59. Ali Modarressi, Ayyoob Imani, Mohsen Fayyaz, and Hinrich Schütze. 2023. Ret-llm: Towards a general read-write memory for large language models. arXiv preprint arXiv:2305.14322. — [arXiv:2305.14322](https://arxiv.org/abs/2305.14322) [find](https://scholar.google.com/scholar?q=Ali+Modarressi%2C+Ayyoob+Imani%2C+Mohsen+Fayyaz%2C+and+Hinrich+Sch%C3%BCtze%2E+2023%2E+Ret%2Dllm%3A+Towards+a+general+read%2Dwrite+memory+for+large+language+models%2E+arXiv+preprint+arXiv%3A2305%2E14322%2E+%E2%80%94+%5BarXiv%3A2305%2E14322%5D%28ht)
60. Aaron Mueller, Albert Webson, Jackson Petty, and Tal Linzen. 2024. In-context learning generalizes, but not always robustly: The case of syntax. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1… [find](https://scholar.google.com/scholar?q=Aaron+Mueller%2C+Albert+Webson%2C+Jackson+Petty%2C+and+Tal+Linzen%2E+2024%2E+In%2Dcontext+learning+generalizes%2C+but+not+always+robustly%3A+The+case+of+syntax%2E+In+Proceedings+of+the+2024+Conference+of+the+North+Amer)
61. Martin Pawelczyk, Seth Neel, and Himabindu Lakkaraju. 2024. [In-context unlearning: Language models as few-shot unlearners](https://md.research.elamur.ai/free/en/papers/pawelczyk-2023-context-unlearning-language-models-few/). In International Conference on Machine Learning, pages 40034–40050.
62. Youyang Qu, Ming Ding, Nan Sun, Kanchana Thi-lakarathna, Tianqing Zhu, and Dusit Niyato. 2024. The frontier of data erasure: Machine unlearning for large language models. arXiv preprint arXiv:2403.15779. — [arXiv:2403.15779](https://arxiv.org/abs/2403.15779) [find](https://scholar.google.com/scholar?q=Youyang+Qu%2C+Ming+Ding%2C+Nan+Sun%2C+Kanchana+Thi%2Dlakarathna%2C+Tianqing+Zhu%2C+and+Dusit+Niyato%2E+2024%2E+The+frontier+of+data+erasure%3A+Machine+unlearning+for+large+language+models%2E+arXiv+preprint+arXiv%3A2403%2E157)
63. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in Neural Information Processing Systems, 36.
64. Adam Roberts, Colin Raffel, and Noam Shazeer. 2020. How much knowledge can you pack into the parameters of a language model? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5418–5426. [find](https://scholar.google.com/scholar?q=Adam+Roberts%2C+Colin+Raffel%2C+and+Noam+Shazeer%2E+2020%2E+How+much+knowledge+can+you+pack+into+the+parameters+of+a+language+model%3F+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Langu)
65. Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems, 31. [find](https://scholar.google.com/scholar?q=Ozan+Sener+and+Vladlen+Koltun%2E+2018%2E+Multi%2Dtask+learning+as+multi%2Dobjective+optimization%2E+Advances+in+neural+information+processing+systems%2C+31%2E)
66. Guangyuan Shi, Qimai Li, Wenlong Zhang, Jiaxin Chen, and Xiao-Ming Wu. 2023. Recon: Reducing conflicting gradients from the root for multi-task learning. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Guangyuan+Shi%2C+Qimai+Li%2C+Wenlong+Zhang%2C+Jiaxin+Chen%2C+and+Xiao%2DMing+Wu%2E+2023%2E+Recon%3A+Reducing+conflicting+gradients+from+the+root+for+multi%2Dtask+learning%2E+In+International+Conference+on+Learning+Repres)
67. Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, and Luke Zettlemoyer. 2024. Detecting pretraining data from large language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Weijia+Shi%2C+Anirudh+Ajith%2C+Mengzhou+Xia%2C+Yangsibo+Huang%2C+Daogao+Liu%2C+Terra+Blevins%2C+Danqi+Chen%2C+and+Luke+Zettlemoyer%2E+2024%2E+Detecting+pretraining+data+from+large+language+models%2E+In+International+Conf)
68. Anton Sinitsin, Vsevolod Plokhotnyuk, Dmitry Pyrkin, Sergei Popov, and Artem Babenko. 2019. Editable neural networks. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Anton+Sinitsin%2C+Vsevolod+Plokhotnyuk%2C+Dmitry+Pyrkin%2C+Sergei+Popov%2C+and+Artem+Babenko%2E+2019%2E+Editable+neural+networks%2E+In+International+Conference+on+Learning+Representations%2E)
69. Chenmien Tan, Ge Zhang, and Jie Fu. 2024. Massive editing for large language models via meta learning. In International Conference on Learning Representations. [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+In+International+Conference+on+Learning+Representations%2E)
70. Bozhong Tian, Xiaozhuan Liang, Siyuan Cheng, Qingbin Liu, Mengru Wang, Dianbo Sui, Xi Chen, Huajun Chen, and Ningyu Zhang. 2024. To forget or not? towards practical knowledge unlearning for large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1524–15… [find](https://scholar.google.com/scholar?q=Bozhong+Tian%2C+Xiaozhuan+Liang%2C+Siyuan+Cheng%2C+Qingbin+Liu%2C+Mengru+Wang%2C+Dianbo+Sui%2C+Xi+Chen%2C+Huajun+Chen%2C+and+Ningyu+Zhang%2E+2024%2E+To+forget+or+not%3F+towards+practical+knowledge+unlearning+for+large+lang)
71. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, and 1 others. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
72. Akshaj Kumar Veldanda, Shi-Xiong Zhang, Anirban Das, Supriyo Chakraborty, Stephen Rawls, Sambit Sahu, and Milind Naphade. 2024. Llm surgery: Efficient knowledge unlearning and editing in large language models. arXiv preprint arXiv:2409.13054. — [arXiv:2409.13054](https://arxiv.org/abs/2409.13054) [find](https://scholar.google.com/scholar?q=Akshaj+Kumar+Veldanda%2C+Shi%2DXiong+Zhang%2C+Anirban+Das%2C+Supriyo+Chakraborty%2C+Stephen+Rawls%2C+Sambit+Sahu%2C+and+Milind+Naphade%2E+2024%2E+Llm+surgery%3A+Efficient+knowledge+unlearning+and+editing+in+large+languag)
73. Anton Voronov, Lena Wolf, and Max Ryabinin. 2024. Mind your format: Towards consistent evaluation of in-context learning improvements. In Findings of the Association for Computational Linguistics ACL 2024, pages 6287–6310. [find](https://scholar.google.com/scholar?q=Anton+Voronov%2C+Lena+Wolf%2C+and+Max+Ryabinin%2E+2024%2E+Mind+your+format%3A+Towards+consistent+evaluation+of+in%2Dcontext+learning+improvements%2E+In+Findings+of+the+Association+for+Computational+Linguistics+ACL+)
74. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, and 1 others. 2024a. [A survey on large language model based autonomous agents](https://md.research.elamur.ai/free/en/papers/wang-2023-survey-large-language-model-based/). Frontiers of Computer Science, 18(6):186345.
75. Mengru Wang, Yunzhi Yao, Ziwen Xu, Shuofei Qiao, Shumin Deng, Peng Wang, Xiang Chen, Jia-Chen Gu, Yong Jiang, Pengjun Xie, and 1 others. 2024b. Knowledge mechanisms in large language models: A survey and perspective. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 709… [find](https://scholar.google.com/scholar?q=Mengru+Wang%2C+Yunzhi+Yao%2C+Ziwen+Xu%2C+Shuofei+Qiao%2C+Shumin+Deng%2C+Peng+Wang%2C+Xiang+Chen%2C+Jia%2DChen+Gu%2C+Yong+Jiang%2C+Pengjun+Xie%2C+and+1+others%2E+2024b%2E+Knowledge+mechanisms+in+large+language+models%3A+A+survey+)
76. Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, and Huajun Chen. 2024c. [Detoxifying large language models via knowledge editing](https://md.research.elamur.ai/free/en/papers/wang-2024-detoxifying-large-language-models-knowledge/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long…
77. Peng Wang, Zexi Li, Ningyu Zhang, Ziwen Xu, Yunzhi Yao, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. 2024d. Wise: Rethinking the knowledge memory for lifelong model editing of large language models. Advances in Neural Information Processing Systems, 37. [find](https://scholar.google.com/scholar?q=Peng+Wang%2C+Zexi+Li%2C+Ningyu+Zhang%2C+Ziwen+Xu%2C+Yunzhi+Yao%2C+Yong+Jiang%2C+Pengjun+Xie%2C+Fei+Huang%2C+and+Huajun+Chen%2E+2024d%2E+Wise%3A+Rethinking+the+knowledge+memory+for+lifelong+model+editing+of+large+language+m)
78. Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, and Huajun Chen. 2024e. EasyEdit: An easy-to-use knowledge editing framework for large language models. In Proceedings of the 62nd An… [find](https://scholar.google.com/scholar?q=Peng+Wang%2C+Ningyu+Zhang%2C+Bozhong+Tian%2C+Zekun+Xi%2C+Yunzhi+Yao%2C+Ziwen+Xu%2C+Mengru+Wang%2C+Shengyu+Mao%2C+Xiaohan+Wang%2C+Siyuan+Cheng%2C+Kangwei+Liu%2C+Yuansheng+Ni%2C+Guozhou+Zheng%2C+and+Huajun+Chen%2E+2024e%2E+EasyEdit%3A)
79. Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, and Jundong Li. 2024f. Knowledge editing for [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). ACM Computing Surveys, 57(3):1–37.
80. Xiaohan Wang, Shengyu Mao, Ningyu Zhang, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, and Huajun Chen. 2024g. Editing conceptual knowledge for large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 706–724. [find](https://scholar.google.com/scholar?q=Xiaohan+Wang%2C+Shengyu+Mao%2C+Ningyu+Zhang%2C+Shumin+Deng%2C+Yunzhi+Yao%2C+Yue+Shen%2C+Lei+Liang%2C+Jinjie+Gu%2C+and+Huajun+Chen%2E+2024g%2E+Editing+conceptual+knowledge+for+large+language+models%2E+In+Findings+of+the+Ass)
81. Yuhuai Wu, Markus Norman Rabe, DeLesley Hutchins, and Christian Szegedy. 2022. Memorizing transformers. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yuhuai+Wu%2C+Markus+Norman+Rabe%2C+DeLesley+Hutchins%2C+and+Christian+Szegedy%2E+2022%2E+Memorizing+transformers%2E+In+International+Conference+on+Learning+Representations%2E)
82. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, and 1 others. 2023. [The rise and potential of large language model based agents: A survey](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/). arXiv preprint arXiv:2309.07864.
83. Jin Yao, Eli Chien, Minxin Du, Xinyao Niu, Tianhao Wang, Zezhou Cheng, and Xiang Yue. 2024. [Machine unlearning of pre-trained large language models](https://md.research.elamur.ai/free/en/papers/yao-2024-machine-unlearning-pre-trained-large/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8403–8419.
84. Yuanshun Yao, Xiaojun Xu, and Yang Liu. 2023. [Large language model unlearning](https://md.research.elamur.ai/free/en/papers/yao-2023-large-language-model-unlearning/). arXiv preprint arXiv:2310.10683.
85. 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)
86. Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. [Gradient surgery for multi-task learning](https://md.research.elamur.ai/free/en/papers/yu-2020-gradient-surgery-multi-task-learning/). Advances in Neural Information Processing Systems, 33:5824– 5836.
87. Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, and Yi Ma. 2023. [Investigating the catastrophic forgetting in multimodal large language models](https://md.research.elamur.ai/free/en/papers/zhai-2023-investigating-catastrophic-forgetting-multimodal-large/). arXiv preprint arXiv:2309.10313.
88. Binchi Zhang, Zihan Chen, Cong Shen, and Jundong Li. 2024a. Verification of machine unlearning is fragile. In International Conference on Machine Learning, pages 58717–58738. [find](https://scholar.google.com/scholar?q=Binchi+Zhang%2C+Zihan+Chen%2C+Cong+Shen%2C+and+Jundong+Li%2E+2024a%2E+Verification+of+machine+unlearning+is+fragile%2E+In+International+Conference+on+Machine+Learning%2C+pages+58717%E2%80%9358738%2E)
89. Binchi Zhang, Yushun Dong, Tianhao Wang, and Jundong Li. 2024b. Towards certified unlearning for deep neural networks. In International Conference on Machine Learning, pages 58800–58818. [find](https://scholar.google.com/scholar?q=Binchi+Zhang%2C+Yushun+Dong%2C+Tianhao+Wang%2C+and+Jundong+Li%2E+2024b%2E+Towards+certified+unlearning+for+deep+neural+networks%2E+In+International+Conference+on+Machine+Learning%2C+pages+58800%E2%80%9358818%2E)
90. Binchi Zhang, Xujiang Zhao, Jundong Li, Haifeng Chen, and Zhengzhang Chen. 2026. [Mind the gap in cultural alignment: Task-aware culture management for large language models](https://md.research.elamur.ai/free/en/papers/zhang-2026-mind-gap-cultural-alignment-task/). arXiv preprint arXiv:2602.22475.
91. Ningyu Zhang, Yunzhi Yao, Bozhong Tian, Peng Wang, Shumin Deng, Mengru Wang, Zekun Xi, Shengyu Mao, Jintian Zhang, Yuansheng Ni, and 1 others. 2024c. A comprehensive study of knowledge editing for large language models. arXiv preprint arXiv:2401.01286. [find](https://scholar.google.com/scholar?q=Ningyu+Zhang%2C+Yunzhi+Yao%2C+Bozhong+Tian%2C+Peng+Wang%2C+Shumin+Deng%2C+Mengru+Wang%2C+Zekun+Xi%2C+Shengyu+Mao%2C+Jintian+Zhang%2C+Yuansheng+Ni%2C+and+1+others%2E+2024c%2E+A+comprehensive+study+of+knowledge+editing+for+lar)
92. Ruiqi Zhang, Licong Lin, Yu Bai, and Song Mei. 2024d. [Negative preference optimization: From catastrophic collapse to effective unlearning](https://md.research.elamur.ai/free/en/papers/zhang-2024-negative-preference-optimization-catastrophic-collapse/). In Conference on Language Modeling.
93. Xingxuan Zhang, Haoran Wang, Jiansheng Li, Yuan Xue, Shikai Guan, Renzhe Xu, Hao Zou, Han Yu, and Peng Cui. 2025. Understanding the generalization of in-context learning in transformers: An empirical study. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Xingxuan+Zhang%2C+Haoran+Wang%2C+Jiansheng+Li%2C+Yuan+Xue%2C+Shikai+Guan%2C+Renzhe+Xu%2C+Hao+Zou%2C+Han+Yu%2C+and+Peng+Cui%2E+2025%2E+Understanding+the+generalization+of+in%2Dcontext+learning+in+transformers%3A+An+empirical+)
94. 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? In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4862–4876. [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+In+Proceedings+of+the+2023+Conference+on+Empirical+Me)

*Updated 2 November 2026*