{"id":"https://openalex.org/W7134176005","doi":"https://doi.org/10.1109/bigdata66926.2025.11401449","title":"Benchmarking LLMs for Pairwise Causal Discovery in Biomedical and Multi-Domain Contexts","display_name":"Benchmarking LLMs for Pairwise Causal Discovery in Biomedical and Multi-Domain Contexts","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7134176005","doi":"https://doi.org/10.1109/bigdata66926.2025.11401449"},"language":null,"primary_location":{"id":"doi:10.1109/bigdata66926.2025.11401449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11401449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.15479","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093015229","display_name":"Sydney Anuyah","orcid":"https://orcid.org/0000-0003-1929-841X"},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sydney Anuyah","raw_affiliation_strings":["Indiana University,Indianapolis,USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Indianapolis,USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123691455","display_name":"Sneha Shajee-Mohan","orcid":null},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sneha Shajee-Mohan","raw_affiliation_strings":["Indiana University,Indianapolis,USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Indianapolis,USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123657867","display_name":"Ankit-Singh Chauhan","orcid":null},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankit-Singh Chauhan","raw_affiliation_strings":["Indiana University,Indianapolis,USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Indianapolis,USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121159498","display_name":"S. Chakraborty","orcid":null},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunandan Chakraborty","raw_affiliation_strings":["Indiana University,Indianapolis,USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Indianapolis,USA","institution_ids":["https://openalex.org/I55769427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093015229"],"corresponding_institution_ids":["https://openalex.org/I55769427"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87635535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7953","last_page":"7962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.6866999864578247,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.6866999864578247,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.08669999986886978,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.032999999821186066,"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":0.6762999892234802},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4553000032901764},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.35350000858306885},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.274399995803833}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6762999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48069998621940613},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4221999943256378},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C166151441","wikidata":"https://www.wikidata.org/wiki/Q4923601","display_name":"Causation","level":2,"score":0.27090001106262207}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata66926.2025.11401449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11401449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.15479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.15479","pdf_url":"https://arxiv.org/pdf/2601.15479","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.15479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.15479","pdf_url":"https://arxiv.org/pdf/2601.15479","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2143891888","https://openalex.org/W2567545459","https://openalex.org/W2937815589","https://openalex.org/W2948579453","https://openalex.org/W3021184789","https://openalex.org/W3093972645","https://openalex.org/W3094217983","https://openalex.org/W4285794637","https://openalex.org/W4382721724","https://openalex.org/W4385573153","https://openalex.org/W4387493000","https://openalex.org/W4389518710","https://openalex.org/W4404188625","https://openalex.org/W4404781206","https://openalex.org/W4405920904","https://openalex.org/W4406459940","https://openalex.org/W4411120052","https://openalex.org/W4414360800","https://openalex.org/W4415796441"],"related_works":[],"abstract_inverted_index":{"The":[0,97,105],"safe":[1],"deployment":[2],"of":[3,116],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"in":[8,102],"high-stakes":[9],"fields":[10],"like":[11,89],"biomedicine,":[12],"requires":[13],"them":[14],"to":[15,18,85,187],"be":[16],"able":[17],"reason":[19],"about":[20],"cause":[21,72],"and":[22,64,73,92,154,177,183],"effect.":[23],"We":[24,76,160],"investigate":[25],"this":[26],"ability":[27],"by":[28],"testing":[29],"13":[30],"open-source":[31],"LLMs":[32],"on":[33,132,167],"a":[34,58,61,113,162,168],"fundamental":[35],"task:":[36],"pairwise":[37],"causal":[38,62,158],"discovery":[39],"(PCD)":[40],"from":[41,81],"text.":[42],"Our":[43],"benchmark,":[44],"using":[45],"12":[46],"diverse":[47],"datasets,":[48],"evaluates":[49],"two":[50],"core":[51],"skills:":[52],"1)":[53],"\\textbf{Causal":[54,66],"Detection}":[55],"(identifying":[56],"if":[57],"text":[59],"contains":[60],"link)":[63],"2)":[65],"Extraction}":[67],"(pulling":[68],"out":[69],"the":[70,120],"exact":[71],"effect":[74],"phrases).":[75],"tested":[77],"various":[78],"prompting":[79],"methods,":[80],"simple":[82],"instructions":[83],"(zero-shot)":[84],"more":[86,141],"complex":[87],"strategies":[88],"Chain-of-Thought":[90],"(CoT)":[91],"Few-shot":[93],"In-Context":[94],"Learning":[95],"(FICL).":[96],"results":[98],"show":[99],"major":[100],"deficiencies":[101],"current":[103],"models.":[104],"best":[106,121,131],"model":[107],"for":[108,122,140],"detection,":[109],"DeepSeek-R1-Distill-Llama-70B,":[110],"only":[111],"achieved":[112],"mean":[114],"score":[115],"49.57\\%":[117],"($C_{detect}$),":[118],"while":[119],"extraction,":[123],"Qwen2.5-Coder-32B-Instruct,":[124],"reached":[125],"just":[126],"47.12\\%":[127],"($C_{extract}$).":[128],"Models":[129],"performed":[130],"simple,":[133],"explicit,":[134],"single-sentence":[135],"relations.":[136],"However,":[137],"performance":[138],"plummeted":[139],"difficult":[142],"(and":[143],"realistic)":[144],"cases,":[145],"such":[146],"as":[147],"implicit":[148],"relationships,":[149],"links":[150],"spanning":[151],"multiple":[152,157],"sentences,":[153],"texts":[155],"containing":[156],"pairs.":[159],"provide":[161],"unified":[163],"evaluation":[164],"framework,":[165],"built":[166],"dataset":[169],"validated":[170],"with":[171],"high":[172],"inter-annotator":[173],"agreement":[174],"($\u03ba\\ge":[175],"0.758$),":[176],"make":[178],"all":[179],"our":[180],"data,":[181],"code,":[182],"prompts":[184],"publicly":[185],"available":[186,192],"spur":[188],"further":[189],"research.":[190],"\\href{https://github.com/sydneyanuyah/CausalDiscovery}{Code":[191],"here:":[193],"https://github.com/sydneyanuyah/CausalDiscovery}":[194]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2026-03-09T00:00:00"}