{"id":"https://openalex.org/W4412886929","doi":"https://doi.org/10.18653/v1/2025.acl-long.12","title":"Literature Meets Data: A Synergistic Approach to Hypothesis Generation","display_name":"Literature Meets Data: A Synergistic Approach to Hypothesis Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886929","doi":"https://doi.org/10.18653/v1/2025.acl-long.12"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.12","pdf_url":"https://aclanthology.org/2025.acl-long.12.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.12.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102752196","display_name":"Haokun Liu","orcid":"https://orcid.org/0000-0001-5777-1293"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haokun Liu","raw_affiliation_strings":["Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089665236","display_name":"Yang Zhou","orcid":"https://orcid.org/0000-0002-1148-0666"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangqiaoyu Zhou","raw_affiliation_strings":["Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038278283","display_name":"Mingxuan Li","orcid":"https://orcid.org/0000-0001-6217-9382"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingxuan Li","raw_affiliation_strings":["Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenfei Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenfei Yuan","raw_affiliation_strings":["Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079270249","display_name":"Chenhao Tan","orcid":"https://orcid.org/0000-0002-3981-2116"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenhao Tan","raw_affiliation_strings":["Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Chicago  , Tsinghua University  Chicago , IL 60637 , USA","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.3939000070095062,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.3939000070095062,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.34540000557899475,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6523424386978149},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39890551567077637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6523424386978149},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39890551567077637}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.12","pdf_url":"https://aclanthology.org/2025.acl-long.12.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.12","pdf_url":"https://aclanthology.org/2025.acl-long.12.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886929.pdf","grobid_xml":"https://content.openalex.org/works/W4412886929.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"AI":[0,115],"holds":[1],"promise":[2],"for":[3,148,156],"transforming":[4],"scientific":[5,157],"processes,":[6],"including":[7],"hypothesis":[8,12,60,149],"generation.Prior":[9],"work":[10],"on":[11,65,108,130],"generation":[13,150],"can":[14,40],"be":[15],"broadly":[16],"categorized":[17],"into":[18],"theory-driven":[19],"and":[20,30,69,74,86,114,128,139,145,151],"datadriven":[21],"approaches.While":[22],"both":[23],"have":[24],"proven":[25],"effective":[26],"in":[27,104],"generating":[28],"novel":[29],"plausible":[31],"hypotheses,":[32],"it":[33],"remains":[34],"an":[35],"open":[36,153],"question":[37],"whether":[38],"they":[39],"complement":[41],"each":[42],"other.To":[43],"address":[44],"this,":[45],"we":[46,91],"develop":[47],"the":[48,93,99],"first":[49,94],"method":[50,64],"that":[51,71,121,136],"combines":[52],"literature-based":[53,84,138],"insights":[54],"with":[55],"data":[56,75],"to":[57,97],"perform":[58],"LLM-powered":[59],"generation.We":[61],"apply":[62],"our":[63],"five":[66],"different":[67],"datasets":[68],"demonstrate":[70],"integrating":[72,137],"literature":[73],"outperforms":[76],"other":[77],"baselines":[78],"(8.97%":[79],"over":[80,83,88],"fewshot,":[81],"15.75%":[82],"alone,":[85],"3.37%":[87],"data-driven":[89,140],"alone).Additionally,":[90],"conduct":[92],"human":[95,106,122],"evaluation":[96],"assess":[98],"utility":[100],"of":[101],"LLM-generated":[102],"hypotheses":[103],"assisting":[105],"decision-making":[107],"two":[109],"challenging":[110],"tasks:":[111],"deception":[112],"detection":[113],"generated":[116],"content":[117],"detection.Our":[118],"results":[119],"show":[120],"accuracy":[123],"improves":[124],"significantly":[125],"by":[126],"7.44%":[127],"14.19%":[129],"these":[131],"tasks,":[132],"respectively.These":[133],"findings":[134],"suggest":[135],"approaches":[141],"provides":[142],"a":[143],"comprehensive":[144],"nuanced":[146],"framework":[147],"could":[152],"new":[154],"avenues":[155],"inquiry.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}