{"id":"https://openalex.org/W4412889185","doi":"https://doi.org/10.18653/v1/2025.bea-1.65","title":"Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic","display_name":"Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889185","doi":"https://doi.org/10.18653/v1/2025.bea-1.65"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.65","pdf_url":"https://aclanthology.org/2025.bea-1.65.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.bea-1.65.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104160506","display_name":"Zhenjiang Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenjiang Mao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181631","display_name":"Artem Bisliouk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Artem Bisliouk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181632","display_name":"Rohith Reddy Nama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohith Nama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021509994","display_name":"Ivan Ruchkin","orcid":"https://orcid.org/0000-0003-3546-414X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Ruchkin","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":2.8273,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90960636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"882","last_page":"890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9621000289916992,"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"}},"topics":[{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9621000289916992,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9355999827384949,"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/computer-science","display_name":"Computer science","score":0.6333967447280884},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45733198523521423},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.4161073863506317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3466123342514038},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2234448790550232},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06105321645736694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6333967447280884},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45733198523521423},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.4161073863506317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3466123342514038},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2234448790550232},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06105321645736694},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.65","pdf_url":"https://aclanthology.org/2025.bea-1.65.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.bea-1.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.65","pdf_url":"https://aclanthology.org/2025.bea-1.65.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.44999998807907104,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889185.pdf","grobid_xml":"https://content.openalex.org/works/W4412889185.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"impressive":[6],"performance":[7],"in":[8,31],"mathematical":[9],"reasoning":[10,43,108],"tasks":[11],"when":[12],"guided":[13],"by":[14],"Chain-of-Thought":[15],"(CoT)":[16],"prompting.However,":[17],"they":[18],"tend":[19],"to":[20,41,74,99],"produce":[21],"highly":[22],"confident":[23],"yet":[24],"incorrect":[25],"outputs,":[26],"which":[27],"poses":[28],"significant":[29],"risks":[30],"domains":[32],"like":[33],"education,":[34],"where":[35],"users":[36],"may":[37],"lack":[38],"the":[39,107],"expertise":[40],"assess":[42],"steps.To":[44],"address":[45],"this,":[46],"we":[47,69],"propose":[48],"a":[49,57,93],"structured":[50],"framework":[51],"that":[52,83,111],"models":[53],"stepwise":[54],"confidence":[55,88,126],"as":[56,85],"temporal":[58,77],"signal":[59],"and":[60,79,103,118,128],"evaluates":[61],"it":[62],"using":[63],"Signal":[64],"Temporal":[65],"Logic":[66],"(STL).In":[67],"particular,":[68],"define":[70],"formal":[71],"STL-based":[72],"constraints":[73],"capture":[75],"desirable":[76],"properties":[78],"compute":[80],"robustness":[81],"scores":[82],"serve":[84],"structured,":[86],"interpretable":[87],"estimates.Our":[89],"approach":[90,113],"also":[91],"introduces":[92],"set":[94],"of":[95],"uncertainty":[96,122],"reshaping":[97],"strategies":[98],"enforce":[100],"smoothness,":[101],"monotonicity,":[102],"causal":[104],"consistency":[105],"across":[106],"trajectory.Experiments":[109],"show":[110],"our":[112],"consistently":[114],"improves":[115],"calibration":[116],"metrics":[117],"provides":[119],"more":[120],"reliable":[121],"estimates":[123],"than":[124],"conventional":[125],"aggregation":[127],"post-hoc":[129],"calibration.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}