{"id":"https://openalex.org/W4413756801","doi":"https://doi.org/10.1007/s10994-025-06838-6","title":"Mind the gap: from plausible to valid self-explanations in large language models","display_name":"Mind the gap: from plausible to valid self-explanations in large language models","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413756801","doi":"https://doi.org/10.1007/s10994-025-06838-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-025-06838-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06838-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06838-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06838-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000389167","display_name":"Korbinian Randl","orcid":"https://orcid.org/0000-0002-7938-2747"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Korbinian Randl","raw_affiliation_strings":["Department of Computer and Systems Sciences, Stockholm University, Borgarfjordsgatan 12, 164 07, Kista, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-7938-2747","affiliations":[{"raw_affiliation_string":"Department of Computer and Systems Sciences, Stockholm University, Borgarfjordsgatan 12, 164 07, Kista, Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033894687","display_name":"John Pavlopoulos","orcid":"https://orcid.org/0000-0001-9188-7425"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]},{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR","SE"],"is_corresponding":false,"raw_author_name":"John Pavlopoulos","raw_affiliation_strings":["Archimedes, Athena RC, Artemidos 1, 151 25, Marousi, Greece","Department of Computer and Systems Sciences, Stockholm University, Borgarfjordsgatan 12, 164 07, Kista, Sweden","Department of Informatics, Athens University of Economics and Business, 76 Patission, 104 35, Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0001-9188-7425","affiliations":[{"raw_affiliation_string":"Archimedes, Athena RC, Artemidos 1, 151 25, Marousi, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Computer and Systems Sciences, Stockholm University, Borgarfjordsgatan 12, 164 07, Kista, Sweden","institution_ids":["https://openalex.org/I161593684"]},{"raw_affiliation_string":"Department of Informatics, Athens University of Economics and Business, 76 Patission, 104 35, Athens, Greece","institution_ids":["https://openalex.org/I73142707"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046274853","display_name":"Aron Henriksson","orcid":"https://orcid.org/0000-0001-9731-1048"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Aron Henriksson","raw_affiliation_strings":["Department of Computer and Systems Sciences, Stockholm University, Borgarfjordsgatan 12, 164 07, Kista, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-9731-1048","affiliations":[{"raw_affiliation_string":"Department of Computer and Systems Sciences, Stockholm University, Borgarfjordsgatan 12, 164 07, Kista, Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083906578","display_name":"Tony Lindgren","orcid":"https://orcid.org/0000-0001-7713-1381"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tony Lindgren","raw_affiliation_strings":["Department of Computer and Systems Sciences, Stockholm University, Borgarfjordsgatan 12, 164 07, Kista, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-7713-1381","affiliations":[{"raw_affiliation_string":"Department of Computer and Systems Sciences, Stockholm University, Borgarfjordsgatan 12, 164 07, Kista, Sweden","institution_ids":["https://openalex.org/I161593684"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000389167"],"corresponding_institution_ids":["https://openalex.org/I161593684"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.2644,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85283872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"114","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9878000020980835,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.4894953966140747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4061744809150696},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3718763589859009},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.36546221375465393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35661864280700684}],"concepts":[{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4894953966140747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4061744809150696},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3718763589859009},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.36546221375465393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35661864280700684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-025-06838-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06838-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06838-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-025-06838-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06838-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06838-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325669","display_name":"Stockholms Universitet","ror":"https://ror.org/05f0yaq80"},{"id":"https://openalex.org/F7311471023","display_name":"NextGenerationEU","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413756801.pdf","grobid_xml":"https://content.openalex.org/works/W4413756801.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W2091144449","https://openalex.org/W2101105183","https://openalex.org/W2163455955","https://openalex.org/W2251939518","https://openalex.org/W2282821441","https://openalex.org/W2552204443","https://openalex.org/W2562979205","https://openalex.org/W2938704169","https://openalex.org/W2965373594","https://openalex.org/W3034999214","https://openalex.org/W3035422918","https://openalex.org/W3176196997","https://openalex.org/W4206361803","https://openalex.org/W4285246417","https://openalex.org/W4384112004","https://openalex.org/W4387058885","https://openalex.org/W4387799763","https://openalex.org/W4389157038","https://openalex.org/W4390490761","https://openalex.org/W4391709172","https://openalex.org/W4392822465","https://openalex.org/W4400461591","https://openalex.org/W4401306886","https://openalex.org/W4401306979","https://openalex.org/W4402670858","https://openalex.org/W4402683840","https://openalex.org/W4403899614","https://openalex.org/W4406844883","https://openalex.org/W6910788466"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Abstract":[0],"This":[1,188],"paper":[2],"investigates":[3],"the":[4,58,98,119,124,134,150,156,179],"reliability":[5],"of":[6,25,60,121,158,181],"explanations":[7,61,195],"generated":[8],"by":[9,163,170],"large":[10,63],"language":[11,64],"models":[12],"(LLMs)":[13],"when":[14],"prompted":[15],"to":[16,36,177,184,203],"explain":[17],"their":[18],"previous":[19],"output.":[20],"We":[21,153],"evaluate":[22],"two":[23],"kinds":[24],"such":[26],"self-explanations":[27],"(":[28],"SE":[29,81,112,132,146],")\u2014extractive":[30],"and":[31,46,76,95,193],"counterfactual\u2014using":[32],"state-of-the-art":[33],"LLMs":[34],"(1B":[35],"70B":[37],"parameters)":[38],"on":[39,141,205],"three":[40],"different":[41],"classification":[42],"tasks":[43],"(both":[44],"objective":[45],"subjective).":[47],"In":[48],"line":[49],"with":[50,84],"Agarwal":[51],"et":[52],"al.":[53],"(Faithfulness":[54],"versus":[55],"plausibility:":[56],"On":[57],"(Un)reliability":[59],"from":[62],"models.":[65],"2024.":[66],"https://doi.org/10.48550/arXiv.2402.04614":[67],"),":[68,90],"our":[69,208],"findings":[70],"indicate":[71],"a":[72,171,175,198],"gap":[73],"between":[74],"perceived":[75],"actual":[77],"model":[78],"reasoning:":[79,152],"while":[80],"largely":[82],"correlate":[83],"human":[85],"judgment":[86],"(i.e.":[87,102],"are":[88,103,113],"plausible":[89,192],"they":[91],"do":[92],"not":[93,104,114],"fully":[94],"accurately":[96],"follow":[97],"model\u2019s":[99],"decision":[100],"process":[101],"faithful":[105],").":[106],"Additionally,":[107],"we":[108],"show":[109,154],"that":[110,130,155,196],"counterfactual":[111,145,165],"even":[115],"necessarily":[116],"valid":[117,186,194],"in":[118,207],"sense":[120],"actually":[122],"changing":[123],"LLM\u2019s":[125,135,151],"prediction.":[126],"Our":[127],"results":[128],"suggest":[129],"extractive":[131],"provide":[133],"\u201cguess\u201d":[136],"at":[137,167],"an":[138],"explanation":[139],"based":[140],"training":[142],"data.":[143],"Conversely,":[144],"can":[147,160],"help":[148],"understand":[149],"issue":[157],"validity":[159,172],"be":[161],"resolved":[162],"sampling":[164],"candidates":[166],"high":[168],"temperature\u2014followed":[169],"check\u2014and":[173],"introducing":[174],"formula":[176],"estimate":[178],"number":[180],"tries":[182],"needed":[183],"generate":[185],"explanations.":[187],"simple":[189],"method":[190],"produces":[191],"offer":[197],"16":[199],"times":[200],"faster":[201],"alternative":[202],"SHAP":[204],"average":[206],"experiments.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}