学习还是自对齐？对指令微调的再思考
Learning or Self-aligning? Rethinking Instruction Fine-tuning
AI总结：
该研究针对指令微调（IFT）底层机制认知不足的问题，设计知识干预框架解耦其影响因素，发现通过IFT学习额外世界知识难有正向作用甚至有负向影响，且IFT前后内部知识一致性是成功的关键，为相关研究提供支撑。
摘要：
指令微调（Instruction Fine-tuning，IFT）是构建大语言模型（large language models，LLMs）的关键阶段。以往研究主要关注IFT在行为规范迁移与额外世界知识学习方面的作用，但人们对IFT的底层机制的理解仍十分有限。本文设计了一个知识干预框架，将IFT的潜在影响因素解耦，从而可对不同因素进行单独分析。令人意外的是，实验发现试图通过IFT学习额外世界知识通常难以产生正向效果，甚至会带来显著的负面影响。此外，研究还发现，保持IFT前后内部知识的一致性是实现成功IFT的关键因素。这些发现揭示了IFT的底层机制，也为近期的一些研究及未来的潜在研究方向提供了有力支撑。
英文摘要：
Instruction Fine-tuning~(IFT) is a critical phase in building large language models~(LLMs). Previous works mainly focus on the IFT's role in the transfer of behavioral norms and the learning of additional world knowledge. However, the understanding of the underlying mechanisms of IFT remains significantly limited. In this paper, we design a knowledge intervention framework to decouple the potential underlying factors of IFT, thereby enabling individual analysis of different factors. Surprisingly, our experiments reveal that attempting to learn additional world knowledge through IFT often struggles to yield positive impacts and can even lead to markedly negative effects. Further, we discover that maintaining internal knowledge consistency before and after IFT is a critical factor for achieving successful IFT. Our findings reveal the underlying mechanisms of IFT and provide robust support for some very recent and potential future works.
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。
