{"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/moose-chem-large-language-models-for","title":"MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses","arxiv_id":"2410.07076","date":"2024-10-09","proceeding":null,"authors":["Zonglin Yang","Wanhao Liu","Ben Gao","Tong Xie","Yuqiang Li","Wanli Ouyang","Soujanya Poria","Erik Cambria","Dongzhan Zhou"],"abstract":"Scientific discovery plays a pivotal role in advancing human society, and recent progress in large language models (LLMs) suggests their potential to accelerate this process. However, it remains unclear whether LLMs can autonomously generate novel and valid hypotheses in chemistry. In this work, we investigate whether LLMs can discover high-quality chemistry hypotheses given only a research background-comprising a question and/or a survey-without restriction on the domain of the question. We begin with the observation that hypothesis discovery is a seemingly intractable task. To address this, we propose a formal mathematical decomposition grounded in a fundamental assumption: that most chemistry hypotheses can be composed from a research background and a set of inspirations. This decomposition leads to three practical subtasks-retrieving inspirations, composing hypotheses with inspirations, and ranking hypotheses - which together constitute a sufficient set of subtasks for the overall scientific discovery task. We further develop an agentic LLM framework, MOOSE-Chem, that is a direct implementation of this mathematical decomposition. To evaluate this framework, we construct a benchmark of 51 high-impact chemistry papers published and online after January 2024, each manually annotated by PhD chemists with background, inspirations, and hypothesis. The framework is able to rediscover many hypotheses with high similarity to the groundtruth, successfully capturing the core innovations-while ensuring no data contamination since it uses an LLM with knowledge cutoff date prior to 2024. Finally, based on LLM's surprisingly high accuracy on inspiration retrieval, a task with inherently out-of-distribution nature, we propose a bold assumption: that LLMs may already encode latent scientific knowledge associations not yet recognized by humans.","url_abs":"https://arxiv.org/abs/2410.07076v5","url_pdf":"https://arxiv.org/pdf/2410.07076v5.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":"moose-chem-large-language-models-for","repo_url":"https://github.com/ZonglinY/MOOSE-Chem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"scientific-discovery","task_name":"scientific discovery"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.07076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07076"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZonglinY/MOOSE-Chem","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"418d4d1894f4dce8","entry":"analysis_list_of_list_of_scores","repo":"ZonglinY/MOOSE-Chem","repo_kind":"official","path":"Analysis/analysis.py","file_url":"https://github.com/ZonglinY/MOOSE-Chem/blob/HEAD/Analysis/analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"418d4d1894f4dce8"}},{"code_sha256_prefix":"a46d31273c1cda64","entry":"exchange_order_in_list","repo":"ZonglinY/MOOSE-Chem","repo_kind":"official","path":"Method/utils.py","file_url":"https://github.com/ZonglinY/MOOSE-Chem/blob/HEAD/Method/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a46d31273c1cda64"}},{"code_sha256_prefix":"f48e1cf015ec00b1","entry":"instruction_prompts","repo":"ZonglinY/MOOSE-Chem","repo_kind":"official","path":"Method/utils.py","file_url":"https://github.com/ZonglinY/MOOSE-Chem/blob/HEAD/Method/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f48e1cf015ec00b1"}},{"code_sha256_prefix":"bf19b64cc289243b","entry":"recover_raw_background","repo":"ZonglinY/MOOSE-Chem","repo_kind":"official","path":"Method/utils.py","file_url":"https://github.com/ZonglinY/MOOSE-Chem/blob/HEAD/Method/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf19b64cc289243b"}},{"code_sha256_prefix":"6a6bec93afdd68e6","entry":"compare_score_between_gold_insp_and_others","repo":"ZonglinY/MOOSE-Chem","repo_kind":"official","path":"Analysis/analysis.py","file_url":"https://github.com/ZonglinY/MOOSE-Chem/blob/HEAD/Analysis/analysis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a6bec93afdd68e6"}},{"code_sha256_prefix":"939c369e4ba796b5","entry":"compare_score_between_inter_recom_and_self_explore","repo":"ZonglinY/MOOSE-Chem","repo_kind":"official","path":"Analysis/analysis.py","file_url":"https://github.com/ZonglinY/MOOSE-Chem/blob/HEAD/Analysis/analysis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"939c369e4ba796b5"}},{"code_sha256_prefix":"78723528e7ed4b7d","entry":"load_title_abstract","repo":"ZonglinY/MOOSE-Chem","repo_kind":"official","path":"Preprocessing/construct_custom_inspiration_corpus.py","file_url":"https://github.com/ZonglinY/MOOSE-Chem/blob/HEAD/Preprocessing/construct_custom_inspiration_corpus.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78723528e7ed4b7d"}},{"code_sha256_prefix":"ff5aa05e7bb75093","entry":"setup_logger","repo":"ZonglinY/MOOSE-Chem","repo_kind":"official","path":"Method/logging_utils.py","file_url":"https://github.com/ZonglinY/MOOSE-Chem/blob/HEAD/Method/logging_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff5aa05e7bb75093"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}