通过迭代自探索提升大模型多跳问答的推理能力
RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question Answering
- 采用分解-检索-自评三步法，引导模型自我优化推理路径
- 在多个基准上显著提升推理准确率，解决证据整合难题
- 适合需要复杂逻辑推理的应用场景，如智能客服、知识问答
大型语言模型在诸多领域表现优异，但在复杂推理任务如多跳问答（MHQA）中仍面临挑战。MHQA需整合多源证据并处理复杂逻辑依赖，常导致推理错误。尽管检索增强生成（RAG）被广泛用于MHQA，但其在过滤噪声数据和获取全部必要证据方面存在局限。为此，本文提出RISE：通过迭代自探索增强推理能力的新框架。RISE包含三个关键步骤：问题分解、检索后阅读、自省批判。通过持续自探索，该框架帮助模型识别正确推理路径，迭代改进证据整合能力、保持逻辑一致性，从而提升MHQA性能。在多个MHQA基准上的大量实验表明，RISE显著提升了推理准确率与任务表现。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel in many areas but continue to face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA). MHQA requires integrating evidence from diverse sources while managing intricate logical dependencies, often leads to errors in reasoning. Retrieval-Augmented Generation (RAG), widely employed in MHQA tasks, faces challenges in effectively filtering noisy data and retrieving all necessary evidence, thereby limiting its effectiveness in addressing MHQA challenges. To address these challenges, we propose RISE:Reasoning Enhancement via Iterative Self-Exploration, a novel framework designed to enhance models' reasoning capability through iterative self-exploration. Specifically, RISE involves three key steps in addressing MHQA tasks: question decomposition, retrieve-then-read, and self-critique. By leveraging continuous self-exploration, RISE identifies accurate reasoning paths, iteratively self-improving the model's capability to integrate evidence, maintain logical consistency, and enhance performance in MHQA tasks. Extensive experiments on multiple MHQA benchmarks demonstrate that RISE significantly improves reasoning accuracy and task 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。