{"id":"https://openalex.org/W6903538702","doi":"https://doi.org/10.1109/icit64950.2025.11049250","title":"Robustness of Question Answering Systems in the Biomedical Domain: a study of the BioASQ dataset","display_name":"Robustness of Question Answering Systems in the Biomedical Domain: a study of the BioASQ dataset","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W6903538702","doi":"https://doi.org/10.1109/icit64950.2025.11049250"},"language":"en","primary_location":{"id":"doi:10.1109/icit64950.2025.11049250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit64950.2025.11049250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 12th International Conference on Information Technology (ICIT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10871/141295","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Andrew Reeves","orcid":null},"institutions":[{"id":"https://openalex.org/I1332878012","display_name":"BT Group (United Kingdom)","ror":"https://ror.org/00kv9pj15","country_code":"GB","type":"company","lineage":["https://openalex.org/I1332878012"]},{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Reeves","raw_affiliation_strings":["Ulster University,British Telecom Ireland Innovation Centre School of Computing,Belfast,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulster University,British Telecom Ireland Innovation Centre School of Computing,Belfast,UK","institution_ids":["https://openalex.org/I1332878012","https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hang Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hang Dong","raw_affiliation_strings":["University of Exeter,Department of Computer Science,Exeter,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Exeter,Department of Computer Science,Exeter,UK","institution_ids":["https://openalex.org/I23923803"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.16590000689029694,"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/T10028","display_name":"Topic Modeling","score":0.16590000689029694,"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":0.11999999731779099,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.09920000284910202,"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/robustness","display_name":"Robustness (evolution)","score":0.7710000276565552},{"id":"https://openalex.org/keywords/overconfidence-effect","display_name":"Overconfidence effect","score":0.5698999762535095},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5626000165939331},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5566999912261963},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45739999413490295},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.414900004863739},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4092000126838684}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7710000276565552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645000219345093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6212999820709229},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5310999751091003},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.414900004863739},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29750001430511475},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26109999418258667}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icit64950.2025.11049250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit64950.2025.11049250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 12th International Conference on Information Technology (ICIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:ore.exeter.ac.uk:10871/141295","is_oa":true,"landing_page_url":"http://hdl.handle.net/10871/141295","pdf_url":null,"source":{"id":"https://openalex.org/S4306401998","display_name":"Open Research Exeter (University of Exeter)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I23923803","host_organization_name":"University of Exeter","host_organization_lineage":["https://openalex.org/I23923803"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:figshare.com:article/29814650","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Robustness_of_Question_Answering_Systems_in_the_Biomedical_Domain_a_study_of_the_BioASQ_dataset/29814650","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:ore.exeter.ac.uk:10871/141295","is_oa":true,"landing_page_url":"http://hdl.handle.net/10871/141295","pdf_url":null,"source":{"id":"https://openalex.org/S4306401998","display_name":"Open Research Exeter (University of Exeter)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I23923803","host_organization_name":"University of Exeter","host_organization_lineage":["https://openalex.org/I23923803"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314204","display_name":"Invest Northern Ireland","ror":"https://ror.org/00qnrsq87"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robustness":[0],"is":[1,16],"a":[2,101],"critical":[3],"consideration":[4],"when":[5],"integrating":[6],"artificial":[7],"intelligence":[8],"(AI)":[9],"systems":[10],"into":[11],"decision-making":[12],"processes.":[13],"This":[14,42],"concern":[15],"particularly":[17,105],"relevant":[18],"for":[19,89,122,138],"generative":[20],"AI":[21],"systems,":[22],"which":[23],"are":[24],"designed":[25],"to":[26,35],"consistently":[27],"produce":[28],"convincing":[29],"outputs":[30],"but":[31,129],"can":[32],"be":[33],"prone":[34],"hallucinations,":[36],"risking":[37],"overconfidence":[38],"in":[39,106],"their":[40],"outputs.":[41],"paper":[43],"investigates":[44],"the":[45,69,107,130,136],"performance":[46],"of":[47,95,109],"fine-tuning":[48,86],"and":[49,62,76],"retrieval":[50],"augmented":[51],"generation":[52],"(RAG)":[53],"under":[54],"external":[55],"data":[56,123],"quality":[57,124],"perturbations,":[58],"including":[59],"typographical":[60],"errors":[61],"factual":[63],"inaccuracies.":[64],"Results":[65],"from":[66],"experiments":[67],"using":[68],"BioASQ":[70],"Task":[71],"12b":[72],"question":[73],"answering":[74],"dataset":[75],"PubMed":[77],"articles":[78],"showed":[79],"nuanced":[80],"trade-offs,":[81],"with":[82],"either":[83],"RAG":[84],"or":[85,111],"performing":[87],"better":[88],"different":[90],"scenarios.":[91],"Furthermore,":[92],"an":[93,120],"analysis":[94],"LLMs\u2019":[96],"self-reported":[97],"confidence":[98],"scores":[99],"indicated":[100],"tendency":[102],"toward":[103],"overconfidence,":[104],"presence":[108],"inconsistent":[110],"erroneous":[112],"context":[113],"data.":[114],"A":[115],"novel":[116],"mitigation":[117],"strategy,":[118],"leveraging":[119],"LLM":[121],"error":[125],"correction":[126,141],"was":[127],"evaluated,":[128],"results":[131],"demonstrated":[132],"limited":[133],"effectiveness,":[134],"highlighting":[135],"need":[137],"more":[139],"advanced":[140],"techniques.":[142]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}