{"type":"ScholarlyArticle","title":"InstructEdit: Instruction-Based Knowledge Editing for Large Language Models","authors":[{"name":"Ningyu Zhang","slug":"ningyu-zhang","given":"Ningyu","family":"Zhang","affiliation":"Zhejiang University"},{"name":"Bozhong Tian","slug":"bozhong-tian","given":"Bozhong","family":"Tian","affiliation":"Zhejiang University"},{"name":"Siyuan Cheng","slug":"siyuan-cheng","given":"Siyuan","family":"Cheng","affiliation":"Tencent"},{"name":"Xiaozhuan Liang","slug":"xiaozhuan-liang","given":"Xiaozhuan","family":"Liang","affiliation":"Tencent"},{"name":"Yi Hu","slug":"yi-hu","given":"Yi","family":"Hu","affiliation":"Tencent"},{"name":"Kouying Xue","slug":"kouying-xue","given":"Kouying","family":"Xue","affiliation":"Tencent"},{"name":"Yanjie Gou","slug":"yanjie-gou","given":"Yanjie","family":"Gou","affiliation":"Tencent"},{"name":"Xi Chen","slug":"xi-chen","given":"Xi","family":"Chen","affiliation":"Tencent"},{"name":"Huajun Chen","slug":"huajun-chen","given":"Huajun","family":"Chen","affiliation":"Zhejiang University"}],"abstract":"Knowledge editing for large language models can offer an efficient solution to alter a model’s behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited generalizability across tasks, necessitating one distinct editor for each task, significantly hindering the broader applications. To address this, we take the first step to analyze the multi-task generalization issue in knowledge editing. Specifically, we develop an instruction-based editing technique, termed InstructEdit, which facilitates the editor's adaptation to various task performances simultaneously using simple instructions. With only one unified editor for each LLM, we empirically demonstrate that InstructEdit can improve the editor's control, leading to an average 14.86% increase in Reliability in multi-task editing setting. Furthermore, experiments involving holdout unseen task illustrate that InstructEdit consistently surpass previous strong baselines. To further investigate the underlying mechanisms of instruction-based knowledge editing, we analyze the principal components of the editing gradient directions, which unveils that instructions can help control optimization direction with stronger OOD generalization.","doi":"10.24963/ijcai.2024/733","url":"https://ijcai.org/proceedings/2024/733","pdf":"https://ijcai.org/proceedings/2024/0733.pdf","markdown":"https://ijcai.org/proceedings/2024/733.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/733","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Natural Language Processing","track":"Main Track","number":733,"pages":{"first":6633,"last":6641},"keywords":["Natural Language Processing: NLP: Applications","Natural Language Processing: NLP: Language models"],"videos":[],"references":[{"position":1,"raw":"[Akyürek et al., 2023] Afra Feyza Akyürek, Eric Pan, Garry Kuwanto, and Derry Wijaya. Dune: Dataset for unified editing. In EMNLP, 2023.","title":"Dune: Dataset for unified editing","authors":"Akyürek","year":"2023","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Brown et al., 2023] Davis Brown, Charles Godfrey, Cody Nizinski, Jonathan Tu, and Henry Kvinge. Edit at your own risk: evaluating the robustness of edited models to distribution shifts, 2023.","title":"Edit at your own risk: evaluating the robustness of edited models to distribution shifts","authors":"Davis Brown, Charles Godfrey, Cody Nizinski, Jonathan Tu, Henry Kvinge","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cao et al., 2021] Nicola De Cao, Wilker Aziz, and Ivan Titov. Editing factual knowledge in language models. In EMNLP, 2021.","title":"Editing factual knowledge in language models","authors":"Nicola De Cao, Wilker Aziz, Ivan Titov","year":"2021","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheng et al., 2023] Siyuan Cheng, Bozhong Tian, Qingbin Liu, Xi Chen, Yongheng Wang, Huajun Chen, and Ningyu Zhang. Can we edit multimodal large language models? In EMNLP, 2023.","title":"Can we edit multimodal large language models?","authors":"Siyuan Cheng, Bozhong Tian, Qingbin Liu, Xi Chen, Yongheng Wang, Huajun Chen, Ningyu Zhang","year":"2023","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheng et al., 2024] Siyuan Cheng, Ningyu Zhang, Bozhong Tian, Xi Chen, Qingbing Liu, and Huajun Chen. Editing language model-based knowledge graph embeddings. In AAAI, 2024.","title":"Editing language model-based knowledge graph embeddings","authors":"Siyuan Cheng, Ningyu Zhang, Bozhong Tian, Xi Chen, Qingbing Liu, Huajun Chen","year":"2024","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cohen et al., 2023] Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, and Mor Geva. Evaluating the ripple ef- fects of knowledge editing in language models. CoRR, abs/2307.12976, 2023.","title":"Evaluating the ripple effects of knowledge editing in language models","authors":"Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, Mor Geva","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dai et al., 2022] Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, and Furu Wei. Knowledge neurons in pretrained transformers. In ACL, 2022.","title":"Knowledge neurons in pretrained transformers","authors":"Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, Furu Wei","year":"2022","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dong et al., 2022] Qingxiu Dong, Damai Dai, Yifan Song, Jingjing Xu, Zhifang Sui, and Lei Li. Calibrating factual knowledge in pretrained language models. In EMNLP, 2022.","title":"Calibrating factual knowledge in pretrained language models","authors":"Dong","year":"2022","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gandikota et al., 2023] Rohit Gandikota, Joanna Materzyn- ska, Jaden Fiotto-Kaufman, and David Bau. Erasing con- cepts from diffusion models. CoRR, abs/2303.07345, 2023.","title":"Erasing concepts from diffusion models","authors":"Rohit Gandikota, Joanna Materzynska, Jaden Fiotto-Kaufman, David Bau","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gu et al., 2024] Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, and Nanyun Peng. Model editing can hurt general abilities of large language models, 2024.","title":"Model editing can hurt general abilities of large language models","authors":"Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, Nanyun Peng","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gupta et al., 2023] Anshita Gupta, Debanjan Mondal, Ak- shay Krishna Sheshadri, Wenlong Zhao, Xiang Lorraine Li, Sarah Wiegreffe, and Niket Tandon. Editing commonsense knowledge in GPT. In EMNLP, 2023.","title":"Editing commonsense knowledge in GPT","authors":"Gupta","year":"2023","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gupta et al., 2024] Akshat Gupta, Anurag Rao, and Gopala Anumanchipalli. Model editing at scale leads to gradual and catastrophic forgetting, 2024.","title":"Model editing at scale leads to gradual and catastrophic forgetting","authors":"Akshat Gupta, Anurag Rao, Gopala Anumanchipalli","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hartvigsen et al., 2023] Tom Hartvigsen, Swami Sankara- narayanan, Hamid Palangi, Yoon Kim, and Marzyeh Ghas- semi. Aging with GRACE: lifelong model editing with discrete key-value adaptors. In NeurIPS, 2023.","title":"Aging with GRACE: lifelong model editing with discrete key-value adaptors","authors":"Hartvigsen","year":"2023","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hase et al., 2023] Peter Hase, Mohit Bansal, Been Kim, and Asma Ghandeharioun. Does localization inform editing? surprising differences in causality-based localization vs. knowledge editing in language models, 2023.","title":"Does localization inform editing? surprising differences in causality-based localization vs. knowledge editing in language models","authors":"Peter Hase, Mohit Bansal, Been Kim, Asma Ghandeharioun","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Huang et al., 2023] Zeyu Huang, Yikang Shen, Xiaofeng Zhang, Jie Zhou, Wenge Rong, and Zhang Xiong. Transformer-patcher: One mistake worth one neuron. In ICLR, 2023.","title":"Transformer-patcher: One mistake worth one neuron","authors":"Huang","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Huang et al., 2024] Youcheng Huang, Wenqiang Lei, Zheng Zhang, Jiancheng Lv, and Shuicheng Yan. See the un- seen: Better context-consistent knowledge-editing by noises, 2024.","title":"See the unseen: Better context-consistent knowledge-editing by noises","authors":"Huang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ilharco et al., 2023] Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. Editing models with task arithmetic. In ICLR, 2023.","title":"Editing models with task arithmetic","authors":"Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, Ali Farhadi","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ju and Zhang, 2023] Yiming Ju and Zheng Zhang. Klob: a benchmark for assessing knowledge locating methods in language models, 2023.","title":"Klob: a benchmark for assessing knowledge locating methods in language models","authors":"Yiming Ju, Zheng Zhang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Li et al., 2023a] Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. Inference-time intervention: Eliciting truthful answers from a language model. In NeurIPS, 2023.","title":"Inference-time intervention: Eliciting truthful answers from a language model","authors":"Li","year":"2023","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Li et al., 2023b] Xiaopeng Li, Shasha Li, Shezheng Song, Jing Yang, Jun Ma, and Jie Yu. Pmet: Precise model editing in a transformer. 2023.","title":"Pmet: Precise model editing in a transformer","authors":"Li","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Li et al., 2023c] Zhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang, Xi Chen, and Huajun Chen. Unveiling the pitfalls of knowledge editing for large language models. arXiv preprint arXiv:2310.02129, 2023.","title":"Unveiling the pitfalls of knowledge editing for large language models","authors":"Li","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Li et al., 2023d] Zichao Li, Ines Arous, Siva Reddy, and Jackie C. K. Cheung. Evaluating dependencies in fact editing for language models: Specificity and implication awareness. In EMNLP, 2023.","title":"Evaluating dependencies in fact editing for language models: Specificity and implication awareness","authors":"Li","year":"2023","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Liang et al., 2022] Xiaozhuan Liang, Ningyu Zhang, Siyuan Cheng, Zhenru Zhang, Chuanqi Tan, and Huajun Chen. Contrastive demonstration tuning for pre-trained language models. In EMNLP, 2022.","title":"Contrastive demonstration tuning for pre-trained language models","authors":"Liang","year":"2022","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lo et al., 2024] Michelle Lo, Shay B. Cohen, and Fazl Barez. Large language models relearn removed concepts, 2024.","title":"Large language models relearn removed concepts","authors":"Michelle Lo, Shay B Cohen, Fazl Barez","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Ma et al., 2024] Jun-Yu Ma, Jia-Chen Gu, Ningyu Zhang, and Zhen-Hua Ling. Neighboring perturbations of knowl- edge editing on large language models, 2024.","title":"Neighboring perturbations of knowledge editing on large language models","authors":"Jun-Yu Ma, Jia-Chen Gu, Ningyu Zhang, Zhen-Hua Ling","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Mao et al., 2023] Shengyu Mao, Ningyu Zhang, Xiaohan Wang, Mengru Wang, Yunzhi Yao, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. Editing personality for llms. 2023. [Mazzia et al., 2023]","title":"Editing personality for llms","authors":"Mao","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"Vittorio Mazzia, Alessandro Pedrani, Andrea Caciolai, Kay Rottmann, and Davide Bernardi. A survey on knowledge editing of neural networks, 2023.","title":"A survey on knowledge editing of neural networks","authors":"Vittorio Mazzia, Alessandro Pedrani, Andrea Caciolai, Kay Rottmann, Davide Bernardi","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Meng et al., 2022a] Kevin Meng, David Bau, Alex Ando- nian, and Yonatan Belinkov. Locating and editing factual knowledge in GPT. In NeurIPS, 2022.","title":"Locating and editing factual knowledge in GPT","authors":"Meng","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Meng et al., 2022b] Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, and David Bau. Mass-editing memory in a transformer. CoRR, abs/2210.07229, 2022.","title":"Mass-editing memory in a transformer","authors":"Meng","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Mitchell et al., 2022a] Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D. Manning. Fast model editing at scale. In ICLR, 2022.","title":"Fast model editing at scale","authors":"Mitchell","year":"2022","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Mitchell et al., 2022b] Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D. Manning, and Chelsea Finn. Memory-based model editing at scale. In ICML, 2022.","title":"Memory-based model editing at scale","authors":"Mitchell","year":"2022","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Onoe et al., 2023] Yasumasa Onoe, Michael J. Q. Zhang, Shankar Padmanabhan, Greg Durrett, and Eunsol Choi. Can lms learn new entities from descriptions? challenges in propagating injected knowledge. In ACL, 2023. [OpenAI, 2022] OpenAI. Introducing chatgpt. https://openai. com/blog/chatgpt, 2022. [OpenAI, 2023] OpenAI. GPT-4 technical report. CoRR, abs/2303.08774, 2023.","title":"Can lms learn new entities from descriptions? challenges in propagating injected knowledge","authors":"Yasumasa Onoe, J Q Michael, Zhang, Greg Shankar Padmanabhan, Eunsol Durrett, Choi","year":"2022","venue":"OpenAI. Introducing chatgpt","doi":null,"url":"https://openai.com/blog/chatgpt,2022","internal_url":null},{"position":33,"raw":"[Ouyang et al., 2022] Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, and Ryan Lowe. Training language models to follow instructions with human feedback. In NeurIPS, 2022.","title":"Training language models to follow instructions with human feedback","authors":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, Ryan Lowe","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Pinter and Elhadad, 2023] Yuval Pinter and Michael El- hadad. Emptying the ocean with a spoon: Should we edit models? In EMNLP, 2023.","title":"Emptying the ocean with a spoon: Should we edit models?","authors":"Elhadad Pinter, Yuval Pinter, Michael Elhadad","year":"2023","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Radford et al., 2019] Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language models are unsupervised multitask learners. 2019.","title":"Language models are unsupervised multitask learners","authors":"Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Sinitsin et al., 2020] Anton Sinitsin, Vsevolod Plokhotnyuk, Dmitry V. Pyrkin, Sergei Popov, and Artem Babenko. Ed- itable neural networks. In ICLR, 2020.","title":"Editable neural networks","authors":"Anton Sinitsin, Vsevolod Plokhotnyuk, V Dmitry, Sergei Pyrkin, Artem Popov, Babenko","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Su et al., 2023] Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, and Tao Yu. One em- bedder, any task: Instruction-finetuned text embeddings. In ACL, 2023.","title":"One embedder, any task: Instruction-finetuned text embeddings","authors":"Su","year":"2023","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Sun et al., 2023] Tianxiang Sun, Xiaotian Zhang, Zhengfu He, Peng Li, Qinyuan Cheng, Hang Yan, Xiangyang Liu, Yunfan Shao, Qiong Tang, Xingjian Zhao, Ke Chen, Yin- ing Zheng, Zhejian Zhou, Ruixiao Li, Jun Zhan, Yunhua Zhou, Linyang Li, Xiaogui Yang, Lingling Wu, Zhangyue Yin, Xuanjing Huang, and Xipeng Qiu. Moss: Training conversational language models from synthetic data. 2023.","title":"Moss: Training conversational language models from synthetic data","authors":"Tianxiang Sun, Xiaotian Zhang, Zhengfu He, Peng Li, Qinyuan Cheng, Hang Yan, Xiangyang Liu, Yunfan Shao, Qiong Tang, Xingjian Zhao, Ke Chen, Yining Zheng, Zhejian Zhou, Ruixiao Li, Jun Zhan, Yunhua Zhou, Linyang Li, Xiaogui Yang, Lingling Wu, Zhangyue Yin, Xuanjing Huang, Xipeng Qiu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Tan et al., 2024] Chenmien Tan, Ge Zhang, and Jie Fu. Mas- sive editing for large language models via meta learning. In ICLR, 2024.","title":"Massive editing for large language models via meta learning","authors":"Tan","year":"2024","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Touvron et al., 2023] 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. Llama: Open and efficient foundation language models. CoRR, abs/2302.13971, 2023.","title":"Llama: Open and efficient foundation language models","authors":"Touvron","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Wang et al., 2023a] Jiaan Wang, Yunlong Liang, Zengkui Sun, Yuxuan Cao, and Jiarong Xu. Cross-lingual knowledge editing in large language models, 2023.","title":"Cross-lingual knowledge editing in large language models","authors":"Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Wang et al., 2023b] 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. Easyedit: An easy-to-use knowledge editing framework for large language models. CoRR, abs/2308.07269, 2023.","title":"Easyedit: An easy-to-use knowledge editing framework for large language models","authors":"Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Wang et al., 2023c] Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, and Jundong Li. Knowledge editing for large language models: A survey, 2023.","title":"Knowledge editing for large language models: A survey","authors":"Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Wei et al., 2022] Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. Finetuned language models are zero-shot learners. In ICLR, 2022.","title":"Finetuned language models are zero-shot learners","authors":"Jason Wei, Maarten Bosma, Y Vincent, Kelvin Zhao, Adams Wei Guu, Brian Yu, Nan Lester, Andrew M Du, Dai, V Quoc, Le","year":"2022","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Wei et al., 2023] Yifan Wei, Xiaoyan Yu, Huanhuan Ma, Fangyu Lei, Yixuan Weng, Ran Song, and Kang Liu. As- sessing knowledge editing in language models via relation perspective, 2023.","title":"Assessing knowledge editing in language models via relation perspective","authors":"Yifan Wei, Xiaoyan Yu, Huanhuan Ma, Fangyu Lei, Yixuan Weng, Ran Song, Kang Liu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Wu et al., 2023] Suhang Wu, Minlong Peng, Yue Chen, Jin- song Su, and Mingming Sun. Eva-kellm: A new bench- mark for evaluating knowledge editing of llms. CoRR, abs/2308.09954, 2023.","title":"Eva-kellm: A new benchmark for evaluating knowledge editing of llms","authors":"Suhang Wu, Minlong Peng, Yue Chen, Jinsong Su, Mingming Sun","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Xu et al., 2022] Yang Xu, Yutai Hou, and Wanxiang Che. Language anisotropic cross-lingual model editing. ArXiv, abs/2205.12677, 2022.","title":"Language anisotropic cross-lingual model editing","authors":"Yang Xu, Yutai Hou, Wanxiang Che","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Yao et al., 2023] Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, and Ningyu Zhang. Editing large language models: Problems, methods, and opportunities. In EMNLP, 2023.","title":"Editing large language models: Problems, methods, and opportunities","authors":"Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, Ningyu Zhang","year":"2023","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Yin et al., 2024] Xunjian Yin, Jin Jiang, Liming Yang, and Xiaojun Wan. History matters: Temporal knowledge editing in large language model. In AAAI, 2024.","title":"History matters: Temporal knowledge editing in large language model","authors":"Xunjian Yin, Jin Jiang, Liming Yang, Xiaojun Wan","year":"2024","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Yu et al., 2024] Lang Yu, Qin Chen, Jie Zhou, and Liang He. MELO: enhancing model editing with neuron-indexed dynamic lora. In AAAI, 2024.","title":"MELO: enhancing model editing with neuron-indexed dynamic lora","authors":"Lang Yu, Qin Chen, Jie Zhou, Liang He","year":"2024","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Zhang et al., 2023a] Ningyu Zhang, Yunzhi Yao, and Shumin Deng. Editing large language models. In AACL: Tutorial Abstract, 2023.","title":"Editing large language models","authors":"Zhang","year":"2023","venue":"AACL: Tutorial Abstract","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Zhang et al., 2023b] Shengyu Zhang, Linfeng Dong, Xiaoya Li, Sen Zhang, Xiaofei Sun, Shuhe Wang, Jiwei Li, Runyi Hu, Tianwei Zhang, Fei Wu, and Guoyin Wang. Instruc- tion tuning for large language models: A survey. CoRR, abs/2308.10792, 2023.","title":"Instruction tuning for large language models: A survey","authors":"Zhang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Zhang et al., 2024] 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. A comprehensive study of knowledge editing for large language models, 2024.","title":"A comprehensive study of knowledge editing for large language models","authors":"Zhang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Zheng et al., 2023] Ce Zheng, Lei Li, Qingxiu Dong, Yuxuan Fan, Zhiyong Wu, Jingjing Xu, and Baobao Chang. Can we edit factual knowledge by in-context learning? In EMNLP, 2023.","title":"Can we edit factual knowledge by in-context learning?","authors":"Ce Zheng, Lei Li, Qingxiu Dong, Yuxuan Fan, Zhiyong Wu, Jingjing Xu, Baobao Chang","year":"2023","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Zhong et al., 2023] Zexuan Zhong, Zhengxuan Wu, Christo- pher D. Manning, Christopher Potts, and Danqi Chen. Mquake: Assessing knowledge editing in language models via multi-hop questions. In EMNLP, 2023.","title":"Mquake: Assessing knowledge editing in language models via multi-hop questions","authors":"Zhong","year":"2023","venue":"EMNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}