无关的短片段比完整长段更有效，揭示大模型上下文学习中的误导性依赖。
Lost in the Passage: Passage-level In-context Learning Does Not Necessarily Need a "Passage"
- 用无意义短文本替代长段落，性能反而更好
- 模型对提示中的段落注意力极低，信息流微弱
- 适合研究模型真实学习机制或优化提示设计
通过在上下文中加入示例，上下文学习（ICL）使大语言模型在众多任务上表现优异。本文聚焦于生成任务的篇章级长上下文ICL，发现模型无法捕捉示例段落与生成输出之间的内在关联。在单文档问答和干扰项生成两个典型任务上，使用长度仅为原段落1/4且完全无意义的演示段落，性能显著优于原始完整段落。注意力分析与信息流检测显示，模型对段落部分的关注度远低于提示中其他组件，且极少有信息从段落流向其他部分，进一步验证了该发现。此外，针对上下文压缩的实验表明，其他长上下文任务有效的压缩方法不适用于篇章级ICL，因为仅用简短无意义的演示段落即可达到竞争力表现。
原文摘要 · Abstract (English)
By simply incorporating demonstrations into the context, in-context learning (ICL) enables large language models (LLMs) to yield awesome performance on many tasks. In this study, we focus on passage-level long-context ICL for generation tasks and find that LLMs cannot learn the intrinsic relationship between the demonstration passage and the generation output. We conduct experiments with different LLMs on two typical generation tasks including single-document question answering and distractor generation, demonstrating that even a completely meaningless demonstration passage with 1/4 length achieves much better performance than the original full passage. Analysis via attention and information flow reveals that LLMs pay little attention to passages compared to other components in the prompt and little information flows from the passage to other parts of the demonstration, which further confirms our finding. Additionally, experiments on context compression indicate that compression approaches proven effective on other long-context tasks are not suitable for passage-level ICL, since simply using shorter meaningless demonstration passages already achieves competitive performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。