{"id":"https://openalex.org/W7166855482","doi":"https://doi.org/10.18653/v1/2026.bionlp-1.31","title":"Randomized Controlled Trials as the Gold-Standard for Evaluating LLMs: A Primer for Biomedical NLP Researchers","display_name":"Randomized Controlled Trials as the Gold-Standard for Evaluating LLMs: A Primer for Biomedical NLP Researchers","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166855482","doi":"https://doi.org/10.18653/v1/2026.bionlp-1.31"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.bionlp-1.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bionlp-1.31","pdf_url":"https://aclanthology.org/2026.bionlp-1.31.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":"BioNLP 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.bionlp-1.31.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107502949","display_name":"Vicente Iv\u00e1n S\u00e1nchez Carmona","orcid":null},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Vicente Ivan Sanchez Carmona","raw_affiliation_strings":["Ricoh Software Research Center (Beijing) Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ricoh Software Research Center (Beijing) Co. , Ltd","institution_ids":["https://openalex.org/I24193003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139805711","display_name":"Shanshan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shanshan Jiang","raw_affiliation_strings":["Ricoh Software Research Center (Beijing) Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ricoh Software Research Center (Beijing) Co. , Ltd","institution_ids":["https://openalex.org/I24193003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139786610","display_name":"Bin Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bin Dong","raw_affiliation_strings":["Ricoh Software Research Center (Beijing) Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ricoh Software Research Center (Beijing) Co. , Ltd","institution_ids":["https://openalex.org/I24193003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24193003"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.90694839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.15620000660419464,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.15620000660419464,"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/T12648","display_name":"Academic Writing and Publishing","score":0.10610000044107437,"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/T10206","display_name":"Meta-analysis and systematic reviews","score":0.07479999959468842,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/primer","display_name":"Primer (cosmetics)","score":0.43380001187324524},{"id":"https://openalex.org/keywords/randomized-controlled-trial","display_name":"Randomized controlled trial","score":0.3926999866962433},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.33410000801086426},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.2915000021457672}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5812000036239624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5590999722480774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45879998803138733},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.4348999857902527},{"id":"https://openalex.org/C2777563447","wikidata":"https://www.wikidata.org/wiki/Q7243397","display_name":"Primer (cosmetics)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C168563851","wikidata":"https://www.wikidata.org/wiki/Q1436668","display_name":"Randomized controlled trial","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28220000863075256}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.bionlp-1.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bionlp-1.31","pdf_url":"https://aclanthology.org/2026.bionlp-1.31.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":"BioNLP 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.bionlp-1.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bionlp-1.31","pdf_url":"https://aclanthology.org/2026.bionlp-1.31.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":"BioNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166855482.pdf","grobid_xml":"https://content.openalex.org/works/W7166855482.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,82,103,149],"no":[5],"longer":[6],"mere":[7],"laboratory":[8],"objects":[9],"of":[10,64,93,113,122,132,141,167],"study.LLMs":[11],"have":[12,26],"become":[13],"everyday":[14],"tools":[15],"in":[16,110,124],"society":[17],"across":[18],"diverse":[19],"populations":[20],"and":[21,66,75],"domains.In":[22],"clinical":[23,31],"contexts,":[24],"LLMs":[25,45,65,72],"already":[27],"been":[28],"devised":[29],"as":[30,44],"support":[32],"applications.However,":[33],"along":[34],"with":[35],"benefits,":[36],"negative":[37],"or":[38,85],"adverse":[39],"effects":[40],"might":[41],"arise,":[42],"such":[43],"potentially":[46],"providing":[47],"psychologically":[48],"distressing":[49],"advice":[50],"to":[51,97,164,169,173],"adolescents":[52],"when":[53],"used":[54],"for":[55,68,77,177],"mental":[56],"health":[57],"support.This":[58],"raises":[59],"questions":[60],"on":[61,143,154],"the":[62,78,105,111,120,125,133,137,151,165],"benefits":[63],"calls":[67],"real-world":[69],"evaluations:":[70],"Are":[71],"really":[73],"helpful":[74],"effective":[76],"intended":[79],"purposes":[80],"people":[81],"using":[83],"them":[84,88],"will":[86],"use":[87,98,121],"for?To":[89],"answer":[90],"this":[91,156],"type":[92],"question":[94],"we":[95,159],"propose":[96],"Randomized":[99],"Controlled":[100],"Trials":[101],"(RCTs).RCTs":[102],"considered":[104],"most":[106],"strict":[107],"experimental":[108],"design":[109,174],"fields":[112],"Medicine,":[114,148],"Psychiatry,":[115],"Psychology,":[116],"among":[117],"others;":[118],"however,":[119],"RCTs":[123,168],"NLP":[126,134,171],"field":[127,135],"is":[128],"almost":[129],"negligible.In":[130],"spite":[131],"being":[136],"de":[138],"facto":[139],"locus":[140],"research":[142],"LLMs,":[144],"other":[145],"fields,":[146],"prominently":[147],"leading":[150],"RCT":[152,175],"evaluations":[153],"LLMs.In":[155],"primer":[157],"paper,":[158],"present":[160],"a":[161],"concise":[162],"introduction":[163],"principles":[166],"guide":[170],"researchers":[172],"studies":[176],"evaluating":[178],"LLMs.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}