{"id":"https://openalex.org/W4416250945","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228321","title":"Step-Aware Confidence Estimation in Natural Language Reasoning","display_name":"Step-Aware Confidence Estimation in Natural Language Reasoning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250945","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228321"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028009553","display_name":"Changhong Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhong Xia","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088447170","display_name":"Zhendong Liu","orcid":"https://orcid.org/0000-0003-3738-4442"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Liu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087774421","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0002-1963-5319"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102614294","display_name":"Haodi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodi Zhou","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044733681","display_name":"Chongjun Wang","orcid":"https://orcid.org/0000-0002-2628-7033"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjun Wang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17546179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3774999976158142,"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":0.3774999976158142,"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":0.06939999759197235,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0608999989926815,"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/security-token","display_name":"Security token","score":0.5752999782562256},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5157999992370605},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4602999985218048},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4350999891757965},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4083000123500824},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.40459999442100525},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3686000108718872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004999876022339},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4812000095844269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46309998631477356},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4602999985218048},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4440000057220459},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.2833000123500824},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2475046758","https://openalex.org/W2964059111","https://openalex.org/W3034643750","https://openalex.org/W3035441651","https://openalex.org/W3084095723","https://openalex.org/W3101988982","https://openalex.org/W4290994954","https://openalex.org/W4385570776","https://openalex.org/W4385573323","https://openalex.org/W4385734246","https://openalex.org/W4389519449","https://openalex.org/W4389520749","https://openalex.org/W4389523793","https://openalex.org/W4399803256","https://openalex.org/W4401042444","https://openalex.org/W4402671653","https://openalex.org/W4409363988"],"related_works":[],"abstract_inverted_index":{"Confidence":[0,57],"estimation":[1],"for":[2,10,136],"generative":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"is":[8],"critical":[9,35],"assessing":[11],"the":[12,106],"reliability":[13],"of":[14,111],"their":[15],"step-by-step":[16],"reasoning.":[17],"While":[18],"existing":[19,107],"methods":[20],"aggregate":[21],"token":[22,69],"probabilities":[23],"uniformly":[24],"or":[25],"use":[26],"semantic":[27],"weighting,":[28],"they":[29],"often":[30],"overlook":[31],"two":[32],"key":[33],"factors:":[34],"low-probability":[36],"tokens":[37],"within":[38],"individual":[39],"reasoning":[40,64,99],"steps":[41],"and":[42,72,97,124,130],"inconsistencies":[43],"in":[44],"logical":[45,74],"transitions":[46],"between":[47],"consecutive":[48],"steps.":[49],"To":[50],"address":[51],"these":[52],"limitations,":[53],"we":[54],"introduce":[55],"Step-Aware":[56],"Estimation":[58],"(SACE),":[59],"which":[60],"separately":[61],"analyzes":[62],"each":[63],"step,":[65],"capturing":[66],"both":[67],"intra-step":[68],"distribution":[70],"patterns":[71],"inter-step":[73],"transitions.":[75],"These":[76],"features":[77],"are":[78],"then":[79],"integrated":[80],"through":[81],"a":[82,121],"lightweight":[83],"model":[84,131],"to":[85,113],"predict":[86],"confidence":[87],"scores.":[88],"Our":[89],"experiments":[90],"on":[91],"LLMs":[92],"with":[93],"different":[94],"parameter":[95],"sizes":[96],"various":[98],"datasets":[100,129],"demonstrate":[101],"that":[102],"SACE":[103,118],"significantly":[104],"outperforms":[105],"methods,":[108],"achieving":[109],"improvements":[110],"up":[112],"8%":[114],"AUROC":[115],"score.":[116],"Moreover,":[117],"requires":[119],"only":[120],"single":[122],"generation":[123],"shows":[125],"strong":[126],"transferability":[127],"across":[128],"architectures,":[132],"highlighting":[133],"its":[134],"practicality":[135],"real-world":[137],"deployment.":[138]},"counts_by_year":[],"updated_date":"2025-11-28T09:21:02.350171","created_date":"2025-11-14T00:00:00"}