通过分步检索增强科学推理能力，提升大模型对专业文献的理解与应用。
RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval
- 分三步检索：分解问题、生成逻辑查询、精准查找相关文献
- 在多个科学推理数据集上超越基线模型，表现更优
- 适合需要深度知识推理的科研人员与复杂问答场景
科学推理不仅需要长链推理，还需掌握领域术语并适应新发现。为应对这些挑战，我们提出RAISE——一种分步检索增强框架，从真实语料中检索逻辑相关的文档。RAISE包含三个步骤：问题分解、逻辑查询生成和逻辑检索。实验表明，相较于其他基线方法，RAISE在科学推理基准测试中持续表现更优。分析显示，与其它方法不同，RAISE检索的文档不仅在领域知识上相近，且逻辑关联性更强。
原文摘要 · Abstract (English)
Scientific reasoning requires not only long-chain reasoning processes, but also knowledge of domain-specific terminologies and adaptation to updated findings. To deal with these challenges for scientific reasoning, we introduce RAISE, a step-by-step retrieval-augmented framework which retrieves logically relevant documents from in-the-wild corpus. RAISE is divided into three steps: problem decomposition, logical query generation, and logical retrieval. We observe that RAISE consistently outperforms other baselines on scientific reasoning benchmarks. We analyze that unlike other baselines, RAISE retrieves documents that are not only similar in terms of the domain knowledge, but also documents logically more relevant.
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。