---
title: "Soft Prompting for Unlearning in Large Language Models (2025)"
description: "The authors propose SPUL (Soft Prompting for Unlearning). 38 references, cited by 9 papers here."
authors: ["Karuna Bhaila", "Minh-Hao Van", "Xintao Wu"]
year: 2025
venue: "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.naacl-long.204/"
doi: "10.18653/v1/2025.naacl-long.204"
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/bhaila-2025-soft-prompting-unlearning-large-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/bhaila-2025-soft-prompting-unlearning-large-language/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/) / Soft Prompting for Unlearning in Large Language Models

# Soft Prompting for Unlearning in Large Language Models

**Authors:** Karuna Bhaila, Minh-Hao Van and Xintao Wu · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2025](https://md.research.elamur.ai/free/en/venues/naacl/2025/)) · **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/2025.naacl-long.204/) · [PDF](https://aclanthology.org/2025.naacl-long.204.pdf) · [DOI 10.18653/v1/2025.naacl-long.204](https://doi.org/10.18653/v1/2025.naacl-long.204) · [OpenAlex](https://openalex.org/W4411119535)

**Citations:** 7 citations (OpenAlex, 2026-10-14) · [9](https://md.research.elamur.ai/free/en/papers/bhaila-2025-soft-prompting-unlearning-large-language/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Regulations such as GDPR's Right to be Forgotten and CCPA require that people can have their data removed, which for LLMs means making a model behave as if certain training examples had never been seen. Retraining is far too costly, and most existing approaches fine-tune some or all model weights. The authors propose SPUL (Soft Prompting for Unlearning). It keeps the LLM frozen and trains only a small set of continuous prompt tokens, which are prepended to queries at inference time.

Training uses a multi-objective loss with two parts:
- **Forget loss:** pushes forget-set inputs toward a randomly drawn generic label (e.g., *neutral*, *unknown*, *none*).
- **Retain loss:** preserves correct predictions on the remaining data.

SPUL is evaluated on sentiment classification (SST-2, Yelp) and multiple-choice QA, mainly with LLaMA-2-7B, and also with OPT-1.3B and LLaMA-2-13B. It achieves a forgetting–utility trade-off comparable to or better than fine-tuning baselines (QLoRA, GA, RL, GA+KL, GA+GD, NPO+RT). It needs orders of magnitude fewer trainable parameters, and one frozen base model can serve several unlearning tasks.

## Key points
- **Trainable parameters:** With p = 30 prompt tokens, SPUL trains about 604K, 1.19M and 1.49M parameters for OPT-1.3B, LLaMA-2-7B and LLaMA-2-13B. Full fine-tuning would update 1.42B, 6.74B and 13B parameters respectively.
- **LLaMA-2-13B on SST-2:** SPUL keeps test-retain accuracy at 95.50% (QLoRA-tuned model: 96.02%) and lowers test-forget accuracy to 7.38%. Fine-tuning baselines could not be run at this size because of GPU limits.
- **OPT-1.3B on SST-2:** SPUL reaches 91.65% test-retain and 17.87% test-forget accuracy. This is close to the strongest baseline, NPO+RT (94.82% / 7.54%).
- **Training time:** One epoch takes roughly 1020 GPU seconds, similar to GA+KL, GA+GD and NPO+RT. SPUL still backpropagates through the frozen model, but it avoids the cost of updating its weights.
- **Robustness and limitations:** On Yelp, SPUL stays robust with forget sets of over 5000 samples. Its main limitation is that it requires white-box access to the model's gradients, so it applies to open-source LLMs. Generation tasks and attack-based robustness evaluation are left for future work.

*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 Arkansas at Fayetteville](https://md.research.elamur.ai/free/en/universities/university-of-arkansas-at-fayetteville/) — University, Fayetteville, United States · 3 works · 272 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

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Karuna Bhaila, Minh-Hao Van and Xintao Wu. 2025. Soft Prompting for Unlearning in Large Language Models. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).

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

```bibtex
@inproceedings{bhaila2025soft,
  title = {{Soft Prompting for Unlearning in Large Language Models}},
  author = {Karuna Bhaila, Minh-Hao Van and Xintao Wu},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.naacl-long.204},
  url = {https://doi.org/10.18653/v1/2025.naacl-long.204}
}
```

- [← previous SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement](https://md.research.elamur.ai/free/en/papers/jain-2025-simpledoc-multi-modal-document-understanding/)
- [next → Sparks of Science: Hypothesis Generation Using Structured Paper Data](https://md.research.elamur.ai/free/en/papers/o-neill-2025-sparks-science-hypothesis-generation-using/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/)

## References

38 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. 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, EMNLP 2024, Miami, FL, USA, November 12-16, 2024, pages 4276–4292. Association for Computational Lingu…
2. Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot. 2021. Machine unlearning. In 42nd IEEE Symposium on Security and Privacy, SP 2021, San Francisco, CA, USA, 24-27 May 2021. [find](https://scholar.google.com/scholar?q=Lucas+Bourtoule%2C+Varun+Chandrasekaran%2C+Christopher+A%2E+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+42nd+IEEE+Symposium+on+Sec)
3. Yinzhi Cao and Junfeng Yang. 2015. Towards making systems forget with machine unlearning. In 2015 IEEE Symposium on Security and Privacy, SP 2015, San Jose, CA, USA, May 17-21, 2015. [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+SP+2015%2C+San+Jose%2C+CA%2C+USA%2C+May+17%2D21%2C+2015%2E)
4. 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, EMNLP 2023, Singapore, December 6-10, 2023.
5. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. [Think you have solved question answering? try arc, the AI2 reasoning challenge](https://md.research.elamur.ai/free/en/papers/clark-2018-think-have-solved-question-answering/). Preprint, arXiv:1803.05457.
6. Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. [Qlora: Efficient finetuning of quantized llms](https://md.research.elamur.ai/free/en/papers/dettmers-2023-qlora-efficient-finetuning-quantized-llms/). In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 202…
7. Ronen Eldan and Mark Russinovich. 2023. Who’s harry potter? approximate unlearning in llms. Preprint, arXiv:2310.02238. [find](https://scholar.google.com/scholar?q=Ronen+Eldan+and+Mark+Russinovich%2E+2023%2E+Who%E2%80%99s+harry+potter%3F+approximate+unlearning+in+llms%2E+Preprint%2C+arXiv%3A2310%2E02238%2E)
8. Aditya Golatkar, Alessandro Achille, and Stefano Soatto. 2020. Eternal sunshine of the spotless net: Selective forgetting in deep networks. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. [find](https://scholar.google.com/scholar?q=Aditya+Golatkar%2C+Alessandro+Achille%2C+and+Stefano+Soatto%2E+2020%2E+Eternal+sunshine+of+the+spotless+net%3A+Selective+forgetting+in+deep+networks%2E+In+2020+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+R)
9. Micheal Grynbaum and Ryan Mac. 2023. The times sues openai and microsoft over a.i. use of copyrighted work. The New York Times. [find](https://scholar.google.com/scholar?q=Micheal+Grynbaum+and+Ryan+Mac%2E+2023%2E+The+times+sues+openai+and+microsoft+over+a%2Ei%2E+use+of+copyrighted+work%2E+The+New+York+Times%2E)
10. Chuan Guo, Tom Goldstein, Awni Y. Hannun, and Laurens van der Maaten. 2020. Certified data removal from machine learning models. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, Proceedings of Machine Learning Research. [find](https://scholar.google.com/scholar?q=Chuan+Guo%2C+Tom+Goldstein%2C+Awni+Y%2E+Hannun%2C+and+Laurens+van+der+Maaten%2E+2020%2E+Certified+data+removal+from+machine+learning+models%2E+In+Proceedings+of+the+37th+International+Conference+on+Machine+Learning)
11. Joel Jang, Dongkeun Yoon, Sohee Yang, Sungmin Cha, Moontae Lee, Lajanugen Logeswaran, and Minjoon Seo. 2023. [Knowledge unlearning for mitigating privacy risks in language models](https://md.research.elamur.ai/free/en/papers/jang-2022-knowledge-unlearning-mitigating-privacy-risks/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (OPTvolume 1: Long Papers), AC…
12. Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. [The power of scale for parameter-efficient prompt tuning](https://md.research.elamur.ai/free/en/papers/lester-2021-power-scale-parameter-efficient-prompt/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, E…
13. Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D. Li, Ann-Kathrin Dombrowski, Shashwat Goel, Gabriel Mukobi, Nathan Helm-Burger, Rassin Lababidi, Lennart Justen, Andrew B. Liu, Michael Chen, Isabelle Barrass, Oliver Zhang, Xiaoyuan Zhu, Rishub Tamirisa, Bh… [find](https://scholar.google.com/scholar?q=Nathaniel+Li%2C+Alexander+Pan%2C+Anjali+Gopal%2C+Summer+Yue%2C+Daniel+Berrios%2C+Alice+Gatti%2C+Justin+D%2E+Li%2C+Ann%2DKathrin+Dombrowski%2C+Shashwat+Goel%2C+Gabriel+Mukobi%2C+Nathan+Helm%2DBurger%2C+Rassin+Lababidi%2C+Lennart+Ju)
14. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (OPTvolume 1: Long… [find](https://scholar.google.com/scholar?q=Xiang+Lisa+Li+and+Percy+Liang%2E+2021%2E+Prefix%2Dtuning%3A+Optimizing+continuous+prompts+for+generation%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+11t)
15. Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Xiaojun Xu, Yuguang Yao, Hang Li, Kush R. Varshney, Mohit Bansal, Sanmi Koyejo, and Yang Liu. 2024. Rethinking machine unlearning for large language models. 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+Xiaojun+Xu%2C+Yuguang+Yao%2C+Hang+Li%2C+Kush+R%2E+Varshney%2C+Mohit+Bansal%2C+Sanmi+Koyejo%2C+and+Yang+Liu%2E+2024%2E+Rethinking+mac)
16. Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Tam, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2022. [P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks](https://md.research.elamur.ai/free/en/papers/liu-2022-p-tuning-prompt-tuning-can/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (OPTvolume 2: Short Papers), ACL 202…
17. Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2023. [Gpt understands, too](https://md.research.elamur.ai/free/en/papers/liu-2021-gpt-understands-too/). AI Open.
18. Pratyush Maini, Zhili Feng, Avi Schwarzschild, Zachary C. 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/). Preprint, arXiv:2401.06121.
19. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in GPT. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9,… [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+In+Advances+in+Neural+Information+Processing+Systems+35%3A+Annual+Conference+on+Neural)
20. Milad Nasr, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Eric Wallace, Florian Tramèr, and Katherine Lee. 2023. [Scalable extraction of training data from (production) language models](https://md.research.elamur.ai/free/en/papers/nasr-2023-scalable-extraction-training-data-production/). Preprint, arXiv:2311.17035.
21. OpenAI. 2024. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv:2303.08774.
22. Preprint, Martin Pawelczyk, Seth Neel, and Himabindu Lakkaraju. 2024. In-context unlearning: Language models as few-shot unlearners. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. [find](https://scholar.google.com/scholar?q=Preprint%2C+Martin+Pawelczyk%2C+Seth+Neel%2C+and+Himabindu+Lakkaraju%2E+2024%2E+In%2Dcontext+unlearning%3A+Language+models+as+few%2Dshot+unlearners%2E+In+Forty%2Dfirst+International+Conference+on+Machine+Learning%2C+ICML+2)
23. Ayush Sekhari, Jayadev Acharya, Gautam Kamath, and Ananda Theertha Suresh. 2021. Remember what you want to forget: Algorithms for machine unlearning. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14,… [find](https://scholar.google.com/scholar?q=Ayush+Sekhari%2C+Jayadev+Acharya%2C+Gautam+Kamath%2C+and+Ananda+Theertha+Suresh%2E+2021%2E+Remember+what+you+want+to+forget%3A+Algorithms+for+machine+unlearning%2E+In+Advances+in+Neural+Information+Processing+Syste)
24. Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2017. [Membership inference attacks against machine learning models](https://md.research.elamur.ai/free/en/papers/shokri-2016-membership-inference-attacks-against-machine/). In 2017 IEEE Symposium on Security and Privacy, SP 2017, San Jose, CA, USA, May 22-26, 2017.
25. Nianwen Si, Hao Zhang, Heyu Chang, Wenlin Zhang, Dan Qu, and Weiqiang Zhang. 2023. Knowledge unlearning for llms: Tasks, methods, and challenges. Preprint, arXiv:2311.15766. — [arXiv:2311.15766](https://arxiv.org/abs/2311.15766) [find](https://scholar.google.com/scholar?q=Nianwen+Si%2C+Hao+Zhang%2C+Heyu+Chang%2C+Wenlin+Zhang%2C+Dan+Qu%2C+and+Weiqiang+Zhang%2E+2023%2E+Knowledge+unlearning+for+llms%3A+Tasks%2C+methods%2C+and+challenges%2E+Preprint%2C+arXiv%3A2311%2E15766%2E+%E2%80%94+%5BarXiv%3A2311%2E15766%5D%28https)
26. 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 Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 20…
27. Pratiksha Thaker, Yash Maurya, and Virginia Smith. 2024. Guardrail baselines for unlearning in llms. Preprint, arXiv:2403.03329. — [arXiv:2403.03329](https://arxiv.org/abs/2403.03329) [find](https://scholar.google.com/scholar?q=Pratiksha+Thaker%2C+Yash+Maurya%2C+and+Virginia+Smith%2E+2024%2E+Guardrail+baselines+for+unlearning+in+llms%2E+Preprint%2C+arXiv%3A2403%2E03329%2E+%E2%80%94+%5BarXiv%3A2403%2E03329%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2403%2E03329%29)
28. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). Preprint…
29. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017,…
30. Johannes Welbl, Nelson F. Liu, and Matt Gardner. 2017. [Crowdsourcing multiple choice science questions](https://md.research.elamur.ai/free/en/papers/welbl-2017-crowdsourcing-multiple-choice-science-questions/). Preprint, arXiv:1707.06209.
31. Jiaxin Wen, Pei Ke, Hao Sun, Zhexin Zhang, Chengfei Li, Jinfeng Bai, and Minlie Huang. 2023. [Unveiling the implicit toxicity in large language models](https://md.research.elamur.ai/free/en/papers/wen-2023-unveiling-implicit-toxicity-large-language/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023.
32. Xinwei Wu, Junzhuo Li, Minghui Xu, Weilong Dong, Shuangzhi Wu, Chao Bian, and Deyi Xiong. 2023. DEPN: detecting and editing privacy neurons in pre-trained language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10,… [find](https://scholar.google.com/scholar?q=Xinwei+Wu%2C+Junzhuo+Li%2C+Minghui+Xu%2C+Weilong+Dong%2C+Shuangzhi+Wu%2C+Chao+Bian%2C+and+Deyi+Xiong%2E+2023%2E+DEPN%3A+detecting+and+editing+privacy+neurons+in+pre%2Dtrained+language+models%2E+In+Proceedings+of+the+2023+C)
33. Jin Yao, Eli Chien, Minxin Du, Xinyao Niu, Tianhao Wang, Zezhou Cheng, and Xiang Yue. 2024a. [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).
34. Yuanshun Yao, Xiaojun Xu, and Yang Liu. 2024b. [Large language model unlearning](https://md.research.elamur.ai/free/en/papers/yao-2023-large-language-model-unlearning/). Preprint, arXiv:2310.10683.
35. Charles Yu, Sullam Jeoung, Anish Kasi, Pengfei Yu, and Heng Ji. 2023. Unlearning bias in language models by partitioning gradients. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023. [find](https://scholar.google.com/scholar?q=Charles+Yu%2C+Sullam+Jeoung%2C+Anish+Kasi%2C+Pengfei+Yu%2C+and+Heng+Ji%2E+2023%2E+Unlearning+bias+in+language+models+by+partitioning+gradients%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+20)
36. Ruiqi Zhang, Licong Lin, Yu Bai, and Song Mei. 2024. [Negative preference optimization: From catastrophic collapse to effective unlearning](https://md.research.elamur.ai/free/en/papers/zhang-2024-negative-preference-optimization-catastrophic-collapse/). Preprint, arXiv:2404.05868.
37. Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. [Opt: Open pre-trai…](https://md.research.elamur.ai/free/en/papers/zhang-2022-opt-open-pre-trained-transformer/)
38. Xiang Zhang, Junbo Jake Zhao, and Yann LeCun. 2015. [Character-level convolutional networks for text classification](https://md.research.elamur.ai/free/en/papers/zhang-2015-character-level-convolutional-networks-text/). In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada.

*Updated 30 October 2026*