{"id":"https://openalex.org/W7140133586","doi":"https://doi.org/10.18653/v1/2026.eacl-long.78","title":"How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains","display_name":"How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140133586","doi":"https://doi.org/10.18653/v1/2026.eacl-long.78"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.78","pdf_url":null,"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2026.eacl-long.78","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026888891","display_name":"Reza Khanmohammadi","orcid":"https://orcid.org/0000-0002-6484-6983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reza Khanmohammadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039112941","display_name":"Erfan Miahi","orcid":"https://orcid.org/0000-0001-7510-083X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erfan Miahi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031351140","display_name":"Simerjot Kaur","orcid":"https://orcid.org/0000-0002-5863-4749"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simerjot Kaur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070646187","display_name":"Charese Smiley","orcid":"https://orcid.org/0009-0007-5575-2313"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charese Smiley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084093422","display_name":"Ivan Brugere","orcid":"https://orcid.org/0000-0002-2953-3746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Brugere","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001502708","display_name":"Kundan Thind","orcid":"https://orcid.org/0000-0002-8261-6655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kundan S Thind","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130326504","display_name":"Mohammad M. Ghassemi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad M. Ghassemi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40028362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1669","last_page":"1754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.34049999713897705,"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":0.34049999713897705,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.04809999838471413,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.04569999873638153,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5392000079154968},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.516700029373169},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3246000111103058},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.31209999322891235},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.2985000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6008999943733215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418999791145325},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41130000352859497},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26429998874664307},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.78","pdf_url":null,"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.78","pdf_url":null,"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reza":[0],"Khanmohammadi,":[1],"Erfan":[2],"Miahi,":[3],"Simerjot":[4],"Kaur,":[5],"Charese":[6],"Smiley,":[7],"Ivan":[8],"Brugere,":[9],"Kundan":[10],"S":[11],"Thind,":[12],"Mohammad":[13],"M.":[14],"Ghassemi.":[15],"Proceedings":[16],"of":[17,21,25],"the":[18,22,26],"19th":[19],"Conference":[20],"European":[23],"Chapter":[24],"Association":[27],"for":[28],"Computational":[29],"Linguistics":[30],"(Volume":[31],"1:":[32],"Long":[33],"Papers).":[34],"2026.":[35]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}
