{"id":"https://openalex.org/W7139942582","doi":"https://doi.org/10.48550/arxiv.2603.18752","title":"WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification","display_name":"WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139942582","doi":"https://doi.org/10.48550/arxiv.2603.18752"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.18752","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18752","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.18752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130230679","display_name":"Isabel Rio-Torto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rio-Torto, Isabel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013827007","display_name":"Jaime S. Cardoso","orcid":"https://orcid.org/0000-0002-3760-2473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cardoso, Jaime S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075704593","display_name":"Lu\u00eds F. Teixeira","orcid":"https://orcid.org/0000-0002-4050-7880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teixeira, Lu\u00eds F.","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.349700003862381,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.349700003862381,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.24619999527931213,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.13120000064373016,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9106000065803528},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6762999892234802},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.557699978351593},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.517300009727478},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4018999934196472},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.392300009727478},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.38269999623298645},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.3718999922275543}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9106000065803528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713699996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6812000274658203},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6762999892234802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6331999897956848},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3718999922275543},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.18752","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18752","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.18752","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18752","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7380459904670715,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Natural":[0],"language":[1,63,81],"explanations":[2,40,64,82,137,201,221],"provide":[3],"an":[4],"inherently":[5],"human-understandable":[6],"way":[7],"to":[8,44,114,125,183,204],"explain":[9],"black-box":[10,88],"models,":[11],"closely":[12],"reflecting":[13],"how":[14],"radiologists":[15],"convey":[16],"their":[17,78],"diagnoses":[18],"in":[19,86,144],"textual":[20],"reports.":[21],"Most":[22],"works":[23],"explicitly":[24],"supervise":[25],"the":[26,38,45,59,87,151,155,162,165,169,173,184,190,198],"explanation":[27],"generation":[28,60],"process":[29,186],"using":[30,131],"datasets":[31],"annotated":[32],"with":[33,83,98,161],"explanations.":[34,104],"Thus,":[35],"though":[36],"plausible,":[37],"generated":[39,76],"are":[41,202,222],"not":[42],"faithful":[43,127],"model's":[46,89],"reasoning.":[47],"In":[48,150],"this":[49,211],"work,":[50],"we":[51,209],"propose":[52],"WeNLEX,":[53,219],"a":[54,99,215],"weakly":[55],"supervised":[56],"model":[57],"for":[58,65,224],"of":[61,102,164,172,218],"natural":[62,80],"multilabel":[66,156],"chest":[67],"X-ray":[68],"classification.":[69],"Faithfulness":[70],"is":[71,93,123,158],"ensured":[72],"by":[73,176,196,213],"matching":[74],"images":[75],"from":[77],"corresponding":[79],"original":[84],"images,":[85],"feature":[90],"space.":[91],"Plausibility":[92],"maintained":[94],"via":[95],"distribution":[96],"alignment":[97],"small":[100],"database":[101],"clinician-annotated":[103],"We":[105],"empirically":[106],"demonstrate,":[107],"through":[108],"extensive":[109],"validation":[110],"on":[111],"multiple":[112],"metrics":[113],"assess":[115],"faithfulness,":[116],"simulatability,":[117],"diversity,":[118],"and":[119,128,147,208],"plausibility,":[120],"that":[121,180],"WeNLEX":[122,141,167,200],"able":[124],"produce":[126],"plausible":[129],"explanations,":[130],"as":[132,134],"little":[133],"5":[135],"ground-truth":[136],"per":[138],"diagnosis.":[139],"Furthermore,":[140],"can":[142,187],"operate":[143],"both":[145],"post-hoc":[146],"in-model":[148],"settings.":[149],"latter,":[152],"i.e.,":[153],"when":[154],"classifier":[157,175],"trained":[159],"together":[160],"rest":[163],"network,":[166],"improves":[168],"classification":[170],"AUC":[171],"standalone":[174],"2.21%,":[177],"thus":[178],"showing":[179],"adding":[181],"interpretability":[182],"training":[185,214],"actually":[188],"increase":[189],"downstream":[191],"task":[192],"performance.":[193],"Additionally,":[194],"simply":[195],"changing":[197],"database,":[199],"adaptable":[203],"any":[205],"target":[206],"audience,":[207],"showcase":[210],"flexibility":[212],"layman":[216],"version":[217],"where":[220],"simplified":[223],"non-medical":[225],"users.":[226]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-21T00:00:00"}