Learning to Edit: Aligning LLMs with Knowledge Editing
Authors:
- Yuxin JiangYJYuxin Jiang
- Yufei WangYWYufei Wang
- Chuhan WuCWChuhan Wu
- Wanjun ZhongWZWanjun Zhong
- Xingshan ZengXZXingshan Zeng
- Jiahui GaoJGJiahui Gao
- Liangyou LiLLLiangyou Li
- Xin JiangXJXin Jiang
- Lifeng ShangLSLifeng Shang
- Ruiming TangRTRuiming Tang
- Qun LiuQLQun Liu
- Wei WangWWWei Wang
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 4689-4705
Abstract
Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Evaluating the Ripple Effects of Knowledge Editing in Language ModelsTransactions of the Association for Computational Linguistics, 2024
- Can We Edit Multimodal Large Language Models?2023
- Lion: Adversarial Distillation of Proprietary Large Language Models2023
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2023
- Knowledge Neurons in Pretrained Transformers2022
- Cross-Task Generalization via Natural Language Crowdsourcing Instructions2022
- Beyond Goldfish Memory: Long-Term Open-Domain Conversation2022
- Editing Factual Knowledge in Language Models2021
- Artificial Intelligence, Values, and AlignmentMinds and Machines, 2020
- PIQA: Reasoning about Physical Commonsense in Natural LanguageProceedings of the AAAI Conference on Artificial Intelligence, 2020