{"id":"https://openalex.org/W7137814967","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-long.68","title":"Fine-grained Confidence Estimation for Spurious Correctness Detection in Large Language Models","display_name":"Fine-grained Confidence Estimation for Spurious Correctness Detection in Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7137814967","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-long.68"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.ijcnlp-long.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.68","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.68.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.ijcnlp-long.68.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107403555","display_name":"Ai Ishii","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ai Ishii","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129738068","display_name":"Naoya Inoue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoya Inoue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100887075","display_name":"Hisami Suzuki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hisami Suzuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129679823","display_name":"Satoshi Sekine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Sekine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.82963688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1238","last_page":"1257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.32519999146461487,"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":0.32519999146461487,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0885000005364418,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.07989999651908875,"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/spurious-relationship","display_name":"Spurious relationship","score":0.685699999332428},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6388999819755554},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.426800012588501},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.334199994802475},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29660001397132874},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.2824000120162964}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.685699999332428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6471999883651733},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6388999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4738999903202057},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3880000114440918},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25209999084472656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.ijcnlp-long.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.68","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.68.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.ijcnlp-long.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.68","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.68.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137814967.pdf","grobid_xml":"https://content.openalex.org/works/W7137814967.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Ai":[0],"Ishii,":[1],"Naoya":[2],"Inoue,":[3],"Hisami":[4],"Suzuki,":[5],"Satoshi":[6],"Sekine.":[7],"Proceedings":[8],"of":[9,23,27],"the":[10,20,24,28],"14th":[11],"International":[12],"Joint":[13],"Conference":[14,22],"on":[15],"Natural":[16],"Language":[17],"Processing":[18],"and":[19],"4th":[21],"Asia-Pacific":[25],"Chapter":[26],"Association":[29],"for":[30],"Computational":[31],"Linguistics.":[32],"2025.":[33]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}
