RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval
This addresses the problem of enhancing scientific reasoning in LLMs, which is domain-specific and incremental.
The paper tackles the challenge of scientific reasoning in LLMs by introducing RAISE, a step-by-step retrieval-augmented framework that retrieves logically relevant documents from in-the-wild corpus, and reports that it consistently outperforms other baselines on scientific reasoning benchmarks.
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.