arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.11905cs.CL
收藏

学习去编辑:通过知识编辑对齐LLMs

Learning to Edit: Aligning LLMs with Knowledge Editing

The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学)

Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang

AI总结:

提出Learning to Edit(LTE)框架,通过两阶段过程教导LLMs将更新知识应用于输入问题,在多基准与架构上展现出优越的知识编辑性能、鲁棒性与低干扰。

摘要:

知识编辑技术旨在高效修改大型语言模型(LLMs)中的小部分知识,同时不负面影响其他输入上的性能,已引起广泛关注。然而,现有方法主要依赖于记忆更新后的知识,阻碍了LLMs在回答问题时将新知识与其固有知识有效结合。为此,我们提出了一种Learning to Edit(LTE)框架,受“授人以渔”理念启发,专注于教导LLMs将更新后的知识应用于输入问题。LTE包含两阶段过程:对齐阶段在精心整理的平行数据集上微调LLMs,以进行可靠的范围内编辑,同时保留范围外信息和语言能力;推理阶段采用基于检索的机制,实现实时和大规模知识编辑。通过在四个流行的知识编辑基准和两种LLM架构上与七种先进基线方法比较,我们证明了LTE在知识编辑性能上的优越性,在批量与序列编辑中的鲁棒性,对一般任务的极小干扰,以及快速的编辑速度。数据和代码可在https://github.com/YJiangcm/LTE获取。

英文摘要:

Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing methods predominantly rely on memorizing the updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions. To this end, we propose a Learning to Edit (LTE) framework, focusing on teaching LLMs to apply updated knowledge into input questions, inspired by the philosophy of "Teach a man to fish." LTE features a two-phase process: (i) the Alignment Phase, which fine-tunes LLMs on a meticulously curated parallel dataset to make reliable, in-scope edits while preserving out-of-scope information and linguistic proficiency; and (ii) the Inference Phase, which employs a retrieval-based mechanism for real-time and mass knowledge editing. By comparing our approach with seven advanced baselines across four popular knowledge editing benchmarks and two LLM architectures, we demonstrate LTE's superiority in knowledge editing performance, robustness in both batch and sequential editing, minimal interference on general tasks, and rapid editing speeds. The data and code are available at https://github.com/YJiangcm/LTE.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑