Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision

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.

@article{zhu2025_2502.20790,
  title={ Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision },
  author={ Dawei Zhu and Xiyu Wei and Guangxiang Zhao and Wenhao Wu and Haosheng Zou and Junfeng Ran and Xun Wang and Lin Sun and Xiangzheng Zhang and Sujian Li },
  journal={arXiv preprint arXiv:2502.20790},
  year={ 2025 }
}