{"id":"https://openalex.org/W7166558251","doi":"https://doi.org/10.63317/3xgwaboh563b","title":"BDI at MEDIQA-EVAL 2026: A ReAct-Style Multimodal Agent for Fine-Grained Medical Response Assessment","display_name":"BDI at MEDIQA-EVAL 2026: A ReAct-Style Multimodal Agent for Fine-Grained Medical Response Assessment","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7166558251","doi":"https://doi.org/10.63317/3xgwaboh563b"},"language":"en","primary_location":{"id":"doi:10.63317/3xgwaboh563b","doi":"https://doi.org/10.63317/3xgwaboh563b","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3xgwaboh563b","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/clinicalnlp/pdf/2026.clinicalnlp-1.16.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/clinicalnlp/pdf/2026.clinicalnlp-1.16.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002461935","display_name":"Justin Xu","orcid":"https://orcid.org/0000-0003-4700-6277","observed_orcids":["https://orcid.org/0000-0003-4700-6277"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Justin Xu","raw_affiliation_strings":["University of Oxford ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford ,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139561250","display_name":"Zizheng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zizheng Zhang","raw_affiliation_strings":["University of Oxford ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford ,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109793706","display_name":"Augustine Luk","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Augustine Luk","raw_affiliation_strings":["University of Oxford ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford ,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Benjamin Khong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Khong","raw_affiliation_strings":["University of California , Los Angeles ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles ,","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135520440","display_name":"Haochen Cui","orcid":"https://orcid.org/0009-0001-1242-4666","observed_orcids":["https://orcid.org/0009-0001-1242-4666"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haochen Cui","raw_affiliation_strings":["University of Oxford ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford ,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143555140","display_name":"Samuel Hwang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Hwang","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001438680","display_name":"Alyssa Pradhan","orcid":"https://orcid.org/0000-0001-9499-0292","observed_orcids":["https://orcid.org/0000-0001-9499-0292"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alyssa Pradhan","raw_affiliation_strings":["University of Oxford ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford ,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050970441","display_name":"Kevin Z Yuan","orcid":"https://orcid.org/0000-0003-1283-2712","observed_orcids":["https://orcid.org/0000-0003-1283-2712"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kevin Yuan","raw_affiliation_strings":["University of Oxford ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford ,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139544437","display_name":"David W. Eyre","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David W. Eyre","raw_affiliation_strings":["University of Oxford ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford ,","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.46839418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8657000064849854,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8657000064849854,"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"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.12370000034570694,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.0017000000225380063,"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/medical-question-answering","display_name":"medical question answering","score":0.621999979019165},{"id":"https://openalex.org/keywords/multimodal-question-answering","display_name":"multimodal question answering","score":0.6980000138282776},{"id":"https://openalex.org/keywords/react-agents","display_name":"ReAct agents","score":0.6880000233650208},{"id":"https://openalex.org/keywords/multimodal-retrieval","display_name":"multimodal retrieval","score":0.7440000176429749},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.6660000085830688},{"id":"https://openalex.org/keywords/image-data-augmentation","display_name":"image augmentation","score":0.7210000157356262},{"id":"https://openalex.org/keywords/multilingual-evaluation","display_name":"multilingual evaluation","score":0.6830000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995000243186951},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.65829998254776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5813999772071838},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4440999925136566},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.4056999981403351},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.33410000801086426},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/3xgwaboh563b","doi":"https://doi.org/10.63317/3xgwaboh563b","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3xgwaboh563b","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/clinicalnlp/pdf/2026.clinicalnlp-1.16.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.63317/3xgwaboh563b","doi":"https://doi.org/10.63317/3xgwaboh563b","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3xgwaboh563b","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/clinicalnlp/pdf/2026.clinicalnlp-1.16.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.8213693499565125}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1139804978","display_name":null,"funder_award_id":"2024-I2M-2\u2013001-1","funder_id":"https://openalex.org/F4320323137","funder_display_name":"Chinese Academy of Medical Sciences"},{"id":"https://openalex.org/G2075850591","display_name":null,"funder_award_id":"NIHR207397","funder_id":"https://openalex.org/F4320318095","funder_display_name":"National Institute for Health Research Health Protection Research Unit"},{"id":"https://openalex.org/G2181228234","display_name":null,"funder_award_id":"NIHR207397","funder_id":"https://openalex.org/F4320319990","funder_display_name":"National Institute for Health and Care Research"}],"funders":[{"id":"https://openalex.org/F4320318095","display_name":"National Institute for Health Research Health Protection Research Unit","ror":null},{"id":"https://openalex.org/F4320319990","display_name":"National Institute for Health and Care Research","ror":"https://ror.org/0187kwz08"},{"id":"https://openalex.org/F4320319994","display_name":"Department of Health and Social Care","ror":"https://ror.org/03sbpja79"},{"id":"https://openalex.org/F4320320290","display_name":"University of Oxford","ror":"https://ror.org/052gg0110"},{"id":"https://openalex.org/F4320323137","display_name":"Chinese Academy of Medical Sciences","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320334506","display_name":"Canadian Institutes of Health Research","ror":"https://ror.org/01gavpb45"},{"id":"https://openalex.org/F4320336045","display_name":"NIHR Oxford Biomedical Research Centre","ror":"https://ror.org/00aps1a34"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166558251.pdf","grobid_xml":"https://content.openalex.org/works/W7166558251.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166548751","https://openalex.org/W7166514703","https://openalex.org/W7166567839","https://openalex.org/W4415315915","https://openalex.org/W7092299418","https://openalex.org/W7164578672","https://openalex.org/W7166532601","https://openalex.org/W4405470182","https://openalex.org/W4417294945","https://openalex.org/W7167456890"],"abstract_inverted_index":{"Free-text":[0],"evaluation":[1,37,49,121,146],"of":[2,20,25,34,58,68,80,125,182],"multimodal":[3,78],"clinical":[4,145,160,187],"question":[5],"answering":[6],"(QA)":[7],"systems":[8,185],"remains":[9],"a":[10,46,62],"central":[11],"challenge":[12,147],"in":[13],"medical":[14,21],"NLP":[15],"due":[16],"to":[17,137],"the":[18,23,32,138,178],"complexity":[19],"knowledge,":[22],"necessity":[24],"integrating":[26],"visual":[27,98],"and":[28,31,93,103,131,168,176,180],"textual":[29],"information,":[30],"limitations":[33,181],"existing":[35],"automatic":[36],"metrics":[38],"for":[39,101,152,186],"open-ended":[40],"outputs.In":[41],"this":[42,135],"work,":[43],"we":[44],"present":[45],"training-free,":[47],"agentic":[48,184],"framework":[50],"that":[51,89,112,148],"formulates":[52],"response":[53],"scoring":[54],"as":[55],"evidence-guided":[56],"orchestration":[57],"components":[59],"rather":[60],"than":[61],"task":[63,141],"requiring":[64],"conventional":[65],"end-to-end":[66],"fine-tuning":[67],"underlying":[69],"LLMs/VLMs.Our":[70],"ReAct-style":[71],"evaluator":[72],"combines":[73],"(i)":[74],"structured":[75,128],"reasoning,":[76],"(ii)":[77],"retrieval":[79],"similar":[81],"encounters,":[82],"(iii)":[83],"auxiliary":[84],"explainable":[85],"feature-based":[86],"regression":[87],"models":[88],"provide":[90],"numeric":[91],"priors":[92],"human-interpretable":[94],"signals,":[95],"(iv)":[96],"VLM-generated":[97],"QA":[99,188],"references":[100],"comparison,":[102],"(v)":[104],"optional":[105],"image":[106],"augmentation":[107],"tools.Unlike":[108],"standard":[109],"LLM-as-a-judge":[110],"approaches":[111],"rely":[113],"on":[114],"direct":[115],"generative":[116],"scoring,":[117],"our":[118],"agent":[119],"decomposes":[120],"into":[122],"modular":[123],"stages":[124],"evidence":[126],"acquisition,":[127],"feature":[129],"modeling,":[130],"integrative":[132],"reasoning.We":[133],"apply":[134],"architecture":[136],"MEDIQA-EVAL":[139],"shared":[140],"-a":[142],"multimodal,":[143],"multilingual":[144],"assesses":[149],"system-generated":[150],"answers":[151],"patient":[153],"queries":[154],"paired":[155],"with":[156],"images":[157],"along":[158],"multiple":[159],"quality":[161],"dimensions.We":[162],"report":[163],"results":[164],"across":[165],"both":[166],"English":[167],"Chinese":[169],"tracks,":[170],"comparing":[171],"against":[172],"baseline":[173],"prompting":[174],"methods,":[175],"discuss":[177],"feasibility":[179],"lightweight":[183],"evaluation.":[189]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-30T00:00:00"}