{"id":"https://openalex.org/W7166820585","doi":"https://doi.org/10.18653/v1/2026.acl-long.669","title":"Generating Literature-Driven Scientific Theories at Scale","display_name":"Generating Literature-Driven Scientific Theories at Scale","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166820585","doi":"https://doi.org/10.18653/v1/2026.acl-long.669"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.669","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.669","pdf_url":"https://aclanthology.org/2026.acl-long.669.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 64th 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/2026.acl-long.669.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123836330","display_name":"Peter Jansen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Jansen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139644852","display_name":"Peter Clark","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Clark","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139836104","display_name":"Doug Downey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doug Downey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139744048","display_name":"Daniel S Weld","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel S Weld","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86896552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14677","last_page":"14698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13516","display_name":"Publishing and Scholarly Communication","score":0.05939999967813492,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13516","display_name":"Publishing and Scholarly Communication","score":0.05939999967813492,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.04580000042915344,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.02759999968111515,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5442000031471252},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2915000021457672},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.25690001249313354},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.24469999969005585}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43309998512268066},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24560000002384186},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.24469999969005585},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.23909999430179596},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.2370000034570694},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.23479999601840973}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.669","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.669","pdf_url":"https://aclanthology.org/2026.acl-long.669.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.669","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.669","pdf_url":"https://aclanthology.org/2026.acl-long.669.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166820585.pdf","grobid_xml":"https://content.openalex.org/works/W7166820585.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contemporary":[0],"automated":[1],"scientific":[2,10,17,44],"discovery":[3],"has":[4],"focused":[5],"on":[6],"agents":[7],"for":[8,85],"generating":[9],"experiments,":[11],"while":[12],"systems":[13],"that":[14,92],"perform":[15],"higher-level":[16],"activities":[18],"such":[19],"as":[20],"theory":[21,47,74],"building":[22],"remain":[23],"underexplored.In":[24],"this":[25],"work,":[26],"we":[27],"formulate":[28],"the":[29],"problem":[30],"of":[31,35,43],"synthesizing":[32],"theories":[33,91],"consisting":[34],"qualitative":[36],"and":[37,67,101],"quantitative":[38],"laws":[39],"from":[40,106],"large":[41],"corpora":[42],"literature.We":[45],"study":[46],"generation":[48,61,71],"at":[49,96,102],"scale,":[50],"using":[51,62,81],"13.7k":[52],"source":[53],"papers":[54],"to":[55,80],"synthesize":[56],"2.9k":[57],"theories,":[58],"examining":[59],"how":[60],"literaturegrounding":[63],"versus":[64,69],"parametric":[65,82],"knowledge,":[66],"accuracy-focused":[68],"novelty-focused":[70],"objectives":[72],"change":[73],"properties.Our":[75],"experiments":[76],"show":[77],"that,":[78],"compared":[79],"LLM":[83],"memory":[84],"generation,":[86],"our":[87],"literature-supported":[88],"method":[89],"creates":[90],"are":[93],"significantly":[94],"better":[95],"both":[97],"matching":[98],"existing":[99],"evidence":[100],"predicting":[103],"future":[104],"results":[105],"4.6k":[107],"subsequently-written":[108],"papers.":[109]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}