通过监督推理路径，显著提升长文本理解的LLM性能。
Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision
- 用自采样和质量评估机制引导模型生成高质量推理链。
- 在长文本问答任务中，性能比传统方法提升13.6点以上。
- 适合需要深度推理的长文本场景，如法律、科研分析。
大语言模型在处理长上下文任务时面临挑战，需在大量输入中推理并聚合关键信息。尽管思维链（CoT）提示在多步推理中表现良好，其在长上下文场景中的效果仍不明确。我们通过跨多种任务的系统性研究发现，CoT的优势在多数长上下文场景中具有泛化性，且随上下文长度增加而增强。基于此，我们提出LongRePS框架，通过过程监督让模型生成高质量推理路径。该框架包含自采样机制以自动生成推理链，以及专为长上下文设计的质量评估协议。在多个长上下文基准测试中，该方法显著优于仅依赖结果监督的基线，在域内任务上（LLaMA/Qwen在MuSiQue上分别+13.6/+3.8点），跨域泛化任务上平均提升+9.3/+8.1点。代码、数据与训练模型已公开，以支持后续研究。
原文摘要 · Abstract (English)
Recent advances in Large Language Models (LLMs) have highlighted the challenge of handling long-context tasks, where models need to reason over extensive input contexts to aggregate target information. While Chain-of-Thought (CoT) prompting has shown promise for multi-step reasoning, its effectiveness for long-context scenarios remains underexplored. Through systematic investigation across diverse tasks, we demonstrate that CoT's benefits generalize across most long-context scenarios and amplify with increasing context length. Motivated by this critical observation, we propose LongRePS, a process-supervised framework that teaches models to generate high-quality reasoning paths for enhanced long-context performance. Our framework incorporates a self-sampling mechanism to bootstrap reasoning paths and a novel quality assessment protocol specifically designed for long-context scenarios. Experimental results on various long-context benchmarks demonstrate the effectiveness of our approach, achieving significant improvements over outcome supervision baselines on both in-domain tasks (+13.6/+3.8 points for LLaMA/Qwen on MuSiQue) and cross-domain generalization (+9.3/+8.1 points on average across diverse QA tasks). Our code, data and trained models are made public to facilitate future research.
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。