Elamur Research⌕
☰
home / papers / 2024 / Detoxifying Large Language Models via Knowledge Editing

Detoxifying Large Language Models via Knowledge Editing

Paper · 2024 · Mengru Wang, Ningyu Zhang, Ziwen Xu et al.

Summary

Safety-aligned LLMs can still be steered into harmful output when a malicious request is wrapped in a carefully engineered jailbreak prompt. The authors ask whether knowledge editing can fix the specific toxic parts of a model instead of only masking them.

To study this, they build SafeEdit, a benchmark that pairs harmful questions with attack templates. Each adversarial query comes with safe and unsafe reference answers, and general instruction-following data is included to check side effects. Evaluation covers three things:

  • blocking the edited attack,
  • resisting unseen (OOD) malicious inputs,
  • preserving normal capabilities.

They test existing editors (MEND, Ext-Sub) alongside SFT and DPO on LLaMA2-7B-Chat and Mistral-7B-v0.1. They also introduce DINM, a baseline that uses a single example to find a toxic layer through contextual semantics and then tunes only that region for a few steps. DINM generalizes best across attacks.

Mechanistic analysis suggests that SFT and DPO mostly route around toxic parameters, whereas DINM partly reduces their toxicity. This points to more lasting detoxification, although edited models sometimes lose fluency and repeat sentences.

Key points

  • How SafeEdit was built:
    • GPT-4 generated 60 harmful questions for each of 9 unsafe categories (540 in total).
    • These were combined with 48 attack prompts gathered from websites, papers and hand-written sources.
    • Unsafe answers came from text-davinci-003 and safe answers from GPT-4.
    • General-performance data was drawn from the Alpaca evaluation set.
  • SafeEdit size and license: 4,050 training, 2,700 validation and 1,350 test instances, released under CC BY-NC-SA 4.0.
  • Quality control: A safety classifier trained on manually annotated data (about 97% accuracy) checked responses, and unsafe ones were corrected by hand.
  • Main result: DINM raised generalized detoxification success from 43.51% to 86.74% on LLaMA2-7B-Chat and from 47.30% to 96.84% on Mistral-7B-v0.1. It needs no extra training and works from one instance.
  • Limitations and availability:
    • Toxic regions are located only at layer level.
    • ROME and MEMIT could not be applied because they require explicit entities.
    • Code and data are available in the EasyEdit repository (github.com/zjunlp/EasyEdit).

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

🎓National University of SingaporeSingapore · Singapore84 works · 32,204 citations🏢Microsoft Research AsiaBeijing · China54 works · 59,921 citations🎓Zhejiang UniversityHangzhou · China46 works · 11,542 citations🎓Westlake UniversityHangzhou · China30 works · 7,732 citations🏢Ant GroupHangzhou · China5 works · 633 citations🎓Southeast UniversityNanjing · China3 works · 233 citations

📚 Shelves 4 Computer Science · 9,086 works Artificial Intelligence · 8,889 works Arts and Humanities · 9,296 works Language and Linguistics · 9,206 works

🧭 Topics 2 Language models & pretraining · 1,343 works Bias, fairness & safety · 209 works

Cite

Cite as Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang and Huajun Chen. 2024. Detoxifying Large Language Models via Knowledge Editing. Proceedings of the 62nd 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. DOI 10.18653/v1/2024.acl-long.171

@inproceedings{wang2024detoxifying,
  title = {{Detoxifying Large Language Models via Knowledge Editing}},
  author = {Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang and Huajun Chen},
  booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2024},
  doi = {10.18653/v1/2024.acl-long.171},
  url = {https://doi.org/10.18653/v1/2024.acl-long.171}
}

References

92 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Afra Feyza Akyürek, Eric Pan, Garry Kuwanto, and Derry Wijaya. 2023. Dune: Dataset for unified editing. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 1847–1861. Association for Computational Linguistics. find
  2. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, Scott Johnston, Sh… find
  3. Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, and Stella Biderman. 2023. LEACE: perfect linear concept erasure in closed form. CoRR, abs/2306.03819. — [arXiv:2306.03819](https://arxiv.org/abs/2306.03819) find
  4. Bochuan Cao, Yuanpu Cao, Lu Lin, and Jinghui Chen. 2023. Defending against alignment-breaking attacks via robustly aligned LLM. CoRR, abs/2309.14348. our card
  5. Yuheng Chen, Pengfei Cao, Yubo Chen, Kang Liu, and Jun Zhao. 2023. Journey to the center of the knowledge neurons: Discoveries of language-independent knowledge neurons and degenerate knowledge neurons. CoRR, abs/2308.13198. — [arXiv:2308.13198](https://arxiv.org/abs/2308.13198) find
  6. Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, and Mor Geva. 2023. Evaluating the ripple effects of knowledge editing in language models. CoRR, abs/2307.12976. find
  7. OpenCompass Contributors. 2023. Opencompass: A universal evaluation platform for foundation models. https://github.com/open-compass/ opencompass. ↗
  8. 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), ACL 2022, Dublin, Ireland, May 22-27, 2022, pages 8493– 8502.… find
  9. Jiawen Deng, Hao Sun, Zhexin Zhang, Jiale Cheng, and Minlie Huang. 2023. Recent advances towards safe, responsible, and moral dialogue systems: A survey. CoRR, abs/2302.09270. — [arXiv:2302.09270](https://arxiv.org/abs/2302.09270) find
  10. Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, and Karthik Narasimhan. 2023. Toxicity in chatgpt: Analyzing persona-assigned language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 1236–1270. Association f… our card
  11. Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao, Yunsen Xian, Jiajun Chen, and Shujian Huang. 2023. A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily. CoRR, abs/2311.08268. find
  12. Zhangyin Feng, Weitao Ma, Weijiang Yu, Lei Huang, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2023. Trends in integration of knowledge and large language models: A survey and taxonomy of methods, benchmarks, and applications. CoRR, abs/2311.05876. — [arXiv:2311.05876](https://arxiv.org/abs/2311.05876) find
  13. Mor Geva, Avi Caciularu, Kevin Wang, and Yoav Goldberg. 2022. Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 30–45, Abu Dhabi, United Arab Emirates. Asso… our card
  14. Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, and Nanyun Peng. 2024. Model editing can hurt general abilities of large language models. CoRR, abs/2401.04700. — [arXiv:2401.04700](https://arxiv.org/abs/2401.04700) find
  15. Akshat Gupta, Anurag Rao, and Gopala Anumanchipalli. 2024. Model editing at scale leads to gradual and catastrophic forgetting. CoRR, abs/2401.07453. find
  16. Anshita Gupta, Debanjan Mondal, Akshay Krishna Sheshadri, Wenlong Zhao, Xiang Lorraine Li, Sarah Wiegreffe, and Niket Tandon. 2023. Editing commonsense knowledge in GPT. CoRR, abs/2305.14956. — [arXiv:2305.14956](https://arxiv.org/abs/2305.14956) find
  17. Skyler Hallinan, Alisa Liu, Yejin Choi, and Maarten Sap. 2023. Detoxifying text with marco: Controllable revision with experts and anti-experts. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2023, Toronto, Canada, July 9-14,… find
  18. Thomas Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim, and Marzyeh Ghassemi. 2022. Aging with GRACE: lifelong model editing with discrete key-value adaptors. CoRR, abs/2211.11031. find
  19. Peter Hase, Mohit Bansal, Been Kim, and Asma Ghandeharioun. 2023. Does localization inform editing? surprising differences in causality-based localization vs. knowledge editing in language models. CoRR, abs/2301.04213. find
  20. Rima Hazra, Sayan Layek, Somnath Banerjee, and Soujanya Poria. 2024. Sowing the wind, reaping the whirlwind: The impact of editing language models. CoRR, abs/2401.10647. find
  21. Xinshuo Hu, Dongfang Li, Zihao Zheng, Zhenyu Liu, Baotian Hu, and Min Zhang. 2023. Separate the wheat from the chaff: Model deficiency unlearning via parameter-efficient module operation. CoRR, abs/2308.08090. — [arXiv:2308.08090](https://arxiv.org/abs/2308.08090) find
  22. Wenyue Hua, Jiang Guo, Mingwen Dong, Henghui Zhu, Patrick Ng, and Zhiguo Wang. 2024. Propagation and pitfalls: Reasoning-based assessment of knowledge editing through counterfactual tasks. CoRR, abs/2401.17585. find
  23. Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu, André Freitas, and Mustafa A. Mustafa. 2023a. A survey of safety and trustworthiness of large language models through… find
  24. Yangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li, and Danqi Chen. 2023b. Catastrophic jailbreak of open-source llms via exploiting generation. CoRR, abs/2310.06987. our card
  25. Youcheng Huang, Wenqiang Lei, Zheng Zhang, Jiancheng Lv, and Shuicheng Yan. 2024. See the unseen: Better context-consistent knowledge-editing by noises. CoRR, abs/2401.07544. — [arXiv:2401.07544](https://arxiv.org/abs/2401.07544) find
  26. Zeyu Huang, Yikang Shen, Xiaofeng Zhang, Jie Zhou, Wenge Rong, and Zhang Xiong. 2023c. Transformer-patcher: One mistake worth one neuron. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. our card
  27. Yoichi Ishibashi and Hidetoshi Shimodaira. 2023. Knowledge sanitization of large language models. CoRR, abs/2309.11852. find
  28. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… find
  29. Mandar Joshi, Eunsol Choi, Daniel S. Weld, and Luke Zettlemoyer. 2017. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. CoRR, abs/1705.03551. our card
  30. Abhinav Kumar, Chenhao Tan, and Amit Sharma. 2022. Probing classifiers are unreliable for concept removal and detection. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - Decembe… find
  31. Andrew Lee, Xiaoyan Bai, Itamar Pres, Martin Wattenberg, Jonathan K. Kummerfeld, and Rada Mihalcea. 2024. A mechanistic understanding of alignment algorithms: A case study on DPO and toxicity. CoRR, abs/2401.01967. find
  32. Chak Tou Leong, Yi Cheng, Jiashuo Wang, Jian Wang, and Wenjie Li. 2023. Self-detoxifying language models via toxification reversal. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 4433–4449. Association for… find
  33. Xiaopeng Li, Shasha Li, Bin Ji, Shezheng Song, Xi Wang, Jun Ma, Jie Yu, Xiaodong Liu, Jing Wang, and Weimin Zhang. 2024. SWEA: changing factual knowledge in large language models via subject word embedding altering. CoRR, abs/2401.17809. — [arXiv:2401.17809](https://arxiv.org/abs/2401.17809) find
  34. Xiaopeng Li, Shasha Li, Shezheng Song, Jing Yang, Jun Ma, and Jie Yu. 2023a. PMET: precise model editing in a transformer. CoRR, abs/2308.08742. find
  35. Xuechen Li, Tianyi Zhang, Yann Dubois, Rohan Taori, Ishaan Gulrajani, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023b. Alpacaeval: An automatic evaluator of instruction-following models. https://github.com/tatsu-lab/alpaca_eval. ↗
  36. Zichao Li, Ines Arous, Siva Reddy, and Jackie Chi Kit Cheung. 2023c. Evaluating dependencies in fact editing for language models: Specificity and implication awareness. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 7623–7636. Associat… find
  37. Yi Liu, Gelei Deng, Zhengzi Xu, Yuekang Li, Yaowen Zheng, Ying Zhang, Lida Zhao, Tianwei Zhang, and Yang Liu. 2023. Jailbreaking chatgpt via prompt engineering: An empirical study. CoRR, abs/2305.13860. our card
  38. Michelle Lo, Shay B. Cohen, and Fazl Barez. 2024. Large language models relearn removed concepts. CoRR, abs/2401.01814. find
  39. Jaime R Lopez. 1996. Intraoperative neurophysiological monitoring. International anesthesiology clinics, 34(4):33–54. find
  40. Xinbei Ma, Tianjie Ju, Jiyang Qiu, Zhuosheng Zhang, Hai Zhao, Lifeng Liu, and Yulong Wang. 2024. Is it possible to edit large language models robustly? CoRR, abs/2402.05827. — [arXiv:2402.05827](https://arxiv.org/abs/2402.05827) find
  41. Vittorio Mazzia, Alessandro Pedrani, Andrea Caciolai, Kay Rottmann, and Davide Bernardi. 2023. A survey on knowledge editing of neural networks. CoRR, abs/2310.19704. — [arXiv:2310.19704](https://arxiv.org/abs/2310.19704) find
  42. Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, and Dilek Hakkani-Tur. 2023. Using in-context learning to improve dialogue safety. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 11882– 1… find
  43. 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
  44. Kevin Meng, Arnab Sen Sharma, Alex J. Andonian, Yonatan Belinkov, and David Bau. 2023. Mass-editing memory in a transformer. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. find
  45. Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D. Manning. 2022a. Fast model editing at scale. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. find
  46. 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, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research, pages 158… find
  47. Silen Naihin, David Atkinson, Marc Green, Mer-wane Hamadi, Craig Swift, Douglas Schonholtz, Adam Tauman Kalai, and David Bau. 2023. Testing language model agents safely in the wild. CoRR, abs/2311.10538. — [arXiv:2311.10538](https://arxiv.org/abs/2311.10538) find
  48. Shashi Narayan, Shay B. Cohen, and Mirella Lapata. 2018. Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization. CoRR, abs/1808.08745. find
  49. OpenAI. 2023. GPT-4 technical report. abs/2303.08774. our card
  50. CoRR, Haowen Pan, Yixin Cao, Xiaozhi Wang, and Xun Yang. 2023. Finding and editing multi-modal neurons in pre-trained transformer. CoRR, abs/2311.07470. — [arXiv:2311.07470](https://arxiv.org/abs/2311.07470) find
  51. Yuval Pinter and Michael Elhadad. 2023. Emptying the ocean with a spoon: Should we edit models? In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 15164–15172. Association for Computational Linguistics. find
  52. Shrimai Prabhumoye, Mostofa Patwary, Mohammad Shoeybi, and Bryan Catanzaro. 2023. Adding instructions during pretraining: Effective way of controlling toxicity in language models. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 202… find
  53. Lianhui Qin, Vered Shwartz, Peter West, Chandra Bhagavatula, Jena D. Hwang, Ronan Le Bras, Antoine Bosselut, and Yejin Choi. 2020. Back to the future: Unsupervised backprop-based decoding for counterfactual and abductive commonsense reasoning. In Proceedings of the 2020 Conference on Empirical Metho… our card
  54. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. CoRR, abs/2305.18290. our card
  55. Alexander Robey, Eric Wong, Hamed Hassani, and George J. Pappas. 2023. Smoothllm: Defending large language models against jailbreaking attacks. CoRR, abs/2310.03684. our card
  56. Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, and Yang Zhang. 2023. "do anything now": Characterizing and evaluating in-the-wild jailbreak prompts on large language models. CoRR, abs/2308.03825. our card
  57. Nianwen Si, Hao Zhang, and Weiqiang Zhang. 2024. MPN: leveraging multilingual patch neuron for cross-lingual model editing. CoRR, abs/2401.03190. — [arXiv:2401.03190](https://arxiv.org/abs/2401.03190) find
  58. Hao Sun, Zhexin Zhang, Jiawen Deng, Jiale Cheng, and Minlie Huang. 2023. Safety assessment of chinese large language models. CoRR, abs/2304.10436. find
  59. Lichao Sun, Yue Huang, Haoran Wang, Siyuan Wu, Qihui Zhang, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li, Zhengliang Liu, Yixin Liu, Yijue Wang, Zhikun Zhang, Bhavya Kailkhura, Caiming Xiong, Chaowei Xiao, Chunyuan Li, Eric P. Xing, Furong Huang, Hao Liu, Heng Ji, Hongyi Wang, Huan Zh… our card
  60. Zecheng Tang, Keyan Zhou, Pinzheng Wang, Yuyang Ding, Juntao Li, and Min Zhang. 2023. Detoxify language model step-by-step. CoRR, abs/2308.08295. — [arXiv:2308.08295](https://arxiv.org/abs/2308.08295) find
  61. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurélien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. CoRR, ab… our card
  62. Binghai Wang, Rui Zheng, Lu Chen, Yan Liu, Shihan Dou, Caishuang Huang, Wei Shen, Senjie Jin, Enyu Zhou, Chenyu Shi, Songyang Gao, Nuo Xu, Yuhao Zhou, Xiaoran Fan, Zhiheng Xi, Jun Zhao, Xiao Wang, Tao Ji, Hang Yan, Lixing Shen, Zhan Chen, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, and… find
  63. Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, and Bo Li. 2023a. Decodingtrust: A comprehensive assessment… our card
  64. Jiaan Wang, Yunlong Liang, Zengkui Sun, Yuxuan Cao, and Jiarong Xu. 2023b. Cross-lingual knowledge editing in large language models. CoRR, abs/2309.08952. find
  65. Peng Wang, Ningyu Zhang, Xin Xie, Yunzhi Yao, Bozhong Tian, Mengru Wang, Zekun Xi, Siyuan Cheng, Kangwei Liu, Guozhou Zheng, et al. 2023c. Easyedit: An easy-to-use knowledge editing framework for large language models. arXiv preprint arXiv:2308.07269. find
  66. Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, and Jundong Li. 2023d. Knowledge editing for large language models: A survey. CoRR, abs/2310.16218. our card
  67. Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, Huilin Wang, Zhaowei Gao, Chunzhao Xie, Chuou Xu, Jihong Dai, Yibin Liu, Jialong Wu, Shengwei Ding, Long Li, Zhiwei Huang, Xinle Deng, Teng Yu, Gangan Ma, Han Xiao, Zixin Chen, Danjun Xiang, Yunxia Wang, Yuanyuan Zhu, Yi Xiao, Jing Wang… find
  68. Weixuan Wang, Barry Haddow, and Alexandra Birch. 2023e. Retrieval-augmented multilingual knowledge editing. CoRR, abs/2312.13040. find
  69. Yiwei Wang, Muhao Chen, Nanyun Peng, and Kai-Wei Chang. 2024c. Deepedit: Knowledge editing as decoding with constraints. CoRR, abs/2401.10471. — [arXiv:2401.10471](https://arxiv.org/abs/2401.10471) find
  70. Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2023a. Jailbroken: How does LLM safety training fail? CoRR, abs/2307.02483. our card
  71. Yifan Wei, Xiaoyan Yu, Huanhuan Ma, Fangyu Lei, Yixuan Weng, Ran Song, and Kang Liu. 2023b. Assessing knowledge editing in language models via relation perspective. CoRR, abs/2311.09053. — [arXiv:2311.09053](https://arxiv.org/abs/2311.09053) find
  72. Zeming Wei, Yifei Wang, and Yisen Wang. 2023c. Jailbreak and guard aligned language models with only few in-context demonstrations. CoRR, abs/2310.06387. our card
  73. Svante Wold, Kim Esbensen, and Paul Geladi. 1987. Principal component analysis. Chemometrics and intelligent laboratory systems, 2(1-3):37–52. find
  74. Suhang Wu, Minlong Peng, Yue Chen, Jinsong Su, and Mingming Sun. 2023a. Eva-kellm: A new benchmark for evaluating knowledge editing of llms. CoRR, abs/2308.09954. — [arXiv:2308.09954](https://arxiv.org/abs/2308.09954) find
  75. Xinwei Wu, Junzhuo Li, Minghui Xu, Weilong Dong, Shuangzhi Wu, Chao Bian, and Deyi Xiong. 2023b. 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
  76. Yueqi Xie, Jingwei Yi, Jiawei Shao, Justin Curl, Lingjuan Lyu, Qifeng Chen, Xing Xie, and Fangzhao Wu. 2023. Defending chatgpt against jailbreak attack via self-reminders. Nat. Mac. Intell., 5(12):1486– 1496. find
  77. Yang Xu, Yutai Hou, Wanxiang Che, and Min Zhang. 2023. Language anisotropic cross-lingual model editing. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pages 5554–5569. Association for Computational Linguistics. find
  78. Jianhao Yan, Futing Wang, Yafu Li, and Yue Zhang. 2024. Potential and challenges of model editing for social debiasing. CoRR. find
  79. Jing Yao, Xiaoyuan Yi, Xiting Wang, Jindong Wang, and Xing Xie. 2023a. From instructions to intrinsic human values - A survey of alignment goals for big models. CoRR, abs/2308.12014. — [arXiv:2308.12014](https://arxiv.org/abs/2308.12014) find
  80. Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Eric Sun, and Yue Zhang. 2023b. A survey on large language model (LLM) security and privacy: The good, the bad, and the ugly. CoRR, abs/2312.02003. our card
  81. Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, and Ningyu Zhang. 2023c. Editing large language models: Problems, methods, and opportunities. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, Dece… find
  82. Xiaoyuan Yi, Jing Yao, Xiting Wang, and Xing Xie. 2023. Unpacking the ethical value alignment in big models. CoRR, abs/2310.17551. — [arXiv:2310.17551](https://arxiv.org/abs/2310.17551) find
  83. Jiahao Yu, Xingwei Lin, Zheng Yu, and Xinyu Xing. 2023a. GPTFUZZER: red teaming large language models with auto-generated jailbreak prompts. CoRR, abs/2309.10253. our card
  84. Lang Yu, Qin Chen, Jie Zhou, and Liang He. 2023b. MELO: enhancing model editing with neuron-indexed dynamic lora. CoRR, abs/2312.11795. — [arXiv:2312.11795](https://arxiv.org/abs/2312.11795) find
  85. Ningyu Zhang, Yunzhi Yao, Bozhong Tian, Peng Wang, Shumin Deng, Mengru Wang, Zekun Xi, Shengyu Mao, Jintian Zhang, Yuansheng Ni, Siyuan Cheng, Ziwen Xu, Xin Xu, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Lei Liang, Zhiqiang Zhang, Xiaowei Zhu, Jun Zhou, and Huajun Chen. 2024. A comprehensive s… find
  86. Xu Zhang and Xiaojun Wan. 2023. Mil-decoding: Detoxifying language models at token-level via multiple instance learning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 190–202. Asso… our card
  87. CoRR, Zhexin Zhang, Junxiao Yang, Pei Ke, and Minlie Huang. 2023c. Defending large language models against jailbreaking attacks through goal prioritization. CoRR, abs/2311.09096. our card
  88. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. 2023. A survey of l… our card
  89. 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, EMNLP 2023, Singapore, December 6-10, 2023, pages 4862– 4876.… find
  90. Chujie Zheng, Fan Yin, Hao Zhou, Fandong Meng, Jie Zhou, Kai-Wei Chang, Minlie Huang, and Nanyun Peng. 2024. Prompt-driven LLM safeguarding via directed representation optimization. CoRR, abs/2401.18018. find
  91. Zexuan Zhong, Zhengxuan Wu, Christopher D. Manning, Christopher Potts, and Danqi Chen. 2023. Mquake: Assessing knowledge editing in language models via multi-hop questions. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10… find
  92. Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, and Dan Hendry… our card

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2024-detoxifying-large-language-models-knowledge/