{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/raise-enhancing-scientific-reasoning-in-llms","title":"RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval","arxiv_id":"2506.08625","date":"2025-06-10","proceeding":null,"authors":["Minhae Oh","Jeonghye Kim","Nakyung Lee","Donggeon Seo","Taeuk Kim","Jungwoo Lee"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2506.08625v1","url_pdf":"https://arxiv.org/pdf/2506.08625v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"raise-enhancing-scientific-reasoning-in-llms","repo_url":"https://github.com/minhaeoh/raise","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"problem-decomposition","task_name":"Problem Decomposition"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}