{"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/literature-meets-data-a-synergistic-approach","title":"Literature Meets Data: A Synergistic Approach to Hypothesis Generation","arxiv_id":"2410.17309","date":"2024-10-22","proceeding":null,"authors":["Haokun Liu","Yangqiaoyu Zhou","Mingxuan Li","Chenfei Yuan","Chenhao Tan"],"abstract":"AI holds promise for transforming scientific processes, including hypothesis generation. Prior work on hypothesis generation can be broadly categorized into theory-driven and data-driven approaches. While both have proven effective in generating novel and plausible hypotheses, it remains an open question whether they can complement each other. To address this, we develop the first method that combines literature-based insights with data to perform LLM-powered hypothesis generation. We apply our method on five different datasets and demonstrate that integrating literature and data outperforms other baselines (8.97\\% over few-shot, 15.75\\% over literature-based alone, and 3.37\\% over data-driven alone). Additionally, we conduct the first human evaluation to assess the utility of LLM-generated hypotheses in assisting human decision-making on two challenging tasks: deception detection and AI generated content detection. Our results show that human accuracy improves significantly by 7.44\\% and 14.19\\% on these tasks, respectively. These findings suggest that integrating literature-based and data-driven approaches provides a comprehensive and nuanced framework for hypothesis generation and could open new avenues for scientific inquiry.","url_abs":"https://arxiv.org/abs/2410.17309v3","url_pdf":"https://arxiv.org/pdf/2410.17309v3.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":"literature-meets-data-a-synergistic-approach","repo_url":"https://github.com/chicagohai/hypothesis-generation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"literature-meets-data-a-synergistic-approach","repo_url":"https://github.com/chicagohai/hypoeval-gen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"literature-meets-data-a-synergistic-approach","repo_url":"https://github.com/chicagohai/hypothesis_generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deception-detection","task_name":"Deception Detection"},{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.17309","atlas_url":"https://app.syntology.ai/?focus=2410.17309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17309"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/chicagohai/hypothesis_generation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chicagohai/hypoeval-gen","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chicagohai/hypothesis-generation","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":4,"ran":3,"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":"6d5c5626595fdd52","entry":"deterministic_hash","repo":"chicagohai/hypoeval-gen","repo_kind":"listed","path":"LLM_wrapper/LLM_cache.py","file_url":"https://github.com/chicagohai/hypoeval-gen/blob/HEAD/LLM_wrapper/LLM_cache.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d5c5626595fdd52"}},{"code_sha256_prefix":"5108e0acf046d399","entry":"get_aspect_definition","repo":"chicagohai/hypoeval-gen","repo_kind":"listed","path":"hypoeval_reproduce/utils.py","file_url":"https://github.com/chicagohai/hypoeval-gen/blob/HEAD/hypoeval_reproduce/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5108e0acf046d399"}},{"code_sha256_prefix":"2a94e8d6e4a50d36","entry":"load_dict","repo":"chicagohai/hypothesis-generation","repo_kind":"official","path":"examples/generation.py","file_url":"https://github.com/chicagohai/hypothesis-generation/blob/HEAD/examples/generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a94e8d6e4a50d36"}},{"code_sha256_prefix":"934bc0ccec801c6f","entry":"load_summeval_train","repo":"chicagohai/hypoeval-gen","repo_kind":"listed","path":"hypoeval_reproduce/utils.py","file_url":"https://github.com/chicagohai/hypoeval-gen/blob/HEAD/hypoeval_reproduce/utils.py","link_basis":"harvester_set","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":"934bc0ccec801c6f"}},{"code_sha256_prefix":"f119782160e58cce","entry":"load_summeval_test","repo":"chicagohai/hypoeval-gen","repo_kind":"listed","path":"hypoeval_reproduce/utils.py","file_url":"https://github.com/chicagohai/hypoeval-gen/blob/HEAD/hypoeval_reproduce/utils.py","link_basis":"harvester_set","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":"f119782160e58cce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}