{"id":"https://openalex.org/W4415062263","doi":"https://doi.org/10.18653/v1/2026.findings-acl.644","title":"ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition","display_name":"ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415062263","doi":"https://doi.org/10.18653/v1/2026.findings-acl.644"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.644","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.644","pdf_url":"https://aclanthology.org/2026.findings-acl.644.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.644.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yujie Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujie Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778571","display_name":"Zonglin Yang","orcid":"https://orcid.org/0000-0002-8059-6654"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zonglin Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017600496","display_name":"Xie Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072407590","display_name":"Jinjie Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinjie Ni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109819194","display_name":"Ben Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108783365","display_name":"Yuqiang Li","orcid":"https://orcid.org/0000-0002-2243-6038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuqiang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030884047","display_name":"Shixiang Tang","orcid":"https://orcid.org/0009-0005-0067-339X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shixiang Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752356","display_name":"Erik Cambria","orcid":"https://orcid.org/0000-0002-3030-1280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik Cambria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112578541","display_name":"Dongzhan Zhou","orcid":"https://orcid.org/0000-0001-6568-5440"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongzhan Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.3728,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96514242,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13187","last_page":"13207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9502999782562256,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9502999782562256,"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/T10028","display_name":"Topic Modeling","score":0.9391999840736389,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7121000289916992},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5722000002861023},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.570900022983551},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4943999946117401},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.43309998512268066},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.40230000019073486}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7121000289916992},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5843999981880188},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5722000002861023},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5343999862670898},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.644","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.644","pdf_url":"https://aclanthology.org/2026.findings-acl.644.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.21248","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.21248","pdf_url":"https://arxiv.org/pdf/2503.21248","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.21248","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21248","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.644","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.644","pdf_url":"https://aclanthology.org/2026.findings-acl.644.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6459390486","display_name":null,"funder_award_id":"2025ZD0121802","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320313434","display_name":"Institute for Catastrophic Loss Reduction","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415062263.pdf","grobid_xml":"https://content.openalex.org/works/W4415062263.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"potential":[6],"in":[7],"assisting":[8],"scientific":[9,46],"research,":[10],"yet":[11],"their":[12,150],"ability":[13,151],"to":[14,22,152],"discover":[15],"high-quality":[16],"research":[17],"hypotheses":[18],"remains":[19],"unexamined":[20],"due":[21],"the":[23,34,64],"lack":[24],"of":[25,45,118,134],"a":[26,42],"dedicated":[27],"benchmark.To":[28],"address":[29],"this":[30,135],"gap,":[31],"we":[32,96],"introduce":[33],"first":[35],"large-scale":[36],"benchmark":[37],"for":[38],"evaluating":[39],"LLMs":[40,143],"on":[41,99],"sufficient":[43,55],"set":[44],"discovery":[47,66,136],"sub-tasks-inspiration":[48],"retrieval,":[49],"hypothesis":[50,53],"composition,":[51],"and":[52,81,130],"ranking-where":[54],"means":[56],"that":[57,73],"perfectly":[58,62],"solving":[59],"these":[60],"sub-tasks":[61],"solves":[63],"overall":[65],"task.We":[67],"develop":[68],"an":[69],"automated":[70,112],"LLM-based":[71],"framework":[72,113],"extracts":[74],"critical":[75],"components-research":[76],"questions,":[77],"background":[78],"surveys,":[79],"inspirations,":[80],"hypotheses-from":[82],"papers":[83,122],"across":[84,141],"12":[85],"disciplines,":[86,142],"with":[87,107],"expert":[88],"validation":[89],"confirming":[90],"its":[91],"accuracy.To":[92],"prevent":[93],"data":[94],"contamination,":[95],"focus":[97],"exclusively":[98],"publications":[100],"from":[101],"2024":[102],"onward,":[103],"ensuring":[104],"minimal":[105],"overlap":[106],"LLM":[108,124],"pretraining":[109,125],"data;":[110],"our":[111],"further":[114],"enables":[115],"automatic":[116,132],"extraction":[117],"even":[119],"more":[120],"recent":[121],"as":[123],"cutoffs":[126],"advance,":[127],"supporting":[128],"scalable":[129],"contamination-free":[131],"renewal":[133],"benchmark.Our":[137],"evaluation":[138],"shows":[139],"that,":[140],"excel":[144],"at":[145],"inspiration":[146],"retrieval-an":[147],"out-of-distribution":[148],"task-suggesting":[149],"surface":[153],"novel":[154],"knowledge":[155],"associations.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-11T00:00:00"}