InstructEdit: Instruction-based Knowledge Editing for Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929329531781120 |
|---|---|
| author | Zhang, Ningyu Tian, Bozhong Cheng, Siyuan Liang, Xiaozhuan Hu, Yi Xue, Kouying Gou, Yanjie Chen, Xi Chen, Huajun |
| author_facet | Zhang, Ningyu Tian, Bozhong Cheng, Siyuan Liang, Xiaozhuan Hu, Yi Xue, Kouying Gou, Yanjie Chen, Xi Chen, Huajun |
| contents | 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. Code and datasets are available in https://github.com/zjunlp/EasyEdit. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16123 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InstructEdit: Instruction-based Knowledge Editing for Large Language Models Zhang, Ningyu Tian, Bozhong Cheng, Siyuan Liang, Xiaozhuan Hu, Yi Xue, Kouying Gou, Yanjie Chen, Xi Chen, Huajun Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning 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. Code and datasets are available in https://github.com/zjunlp/EasyEdit. |
| title | InstructEdit: Instruction-based Knowledge Editing for Large Language Models |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2402.16123 |