{"id":"https://openalex.org/W4416034029","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1205","title":"Temporal Consistency for LLM Reasoning Process Error Identification","display_name":"Temporal Consistency for LLM Reasoning Process Error Identification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034029","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1205"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1205","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1205","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1205.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":"Findings of the Association for Computational Linguistics: EMNLP 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.findings-emnlp.1205.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101936083","display_name":"Jiacheng Guo","orcid":"https://orcid.org/0000-0003-3238-4275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiacheng Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087759995","display_name":"Yue Wu","orcid":"https://orcid.org/0000-0002-9210-5103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004501905","display_name":"Jiahao Qiu","orcid":"https://orcid.org/0000-0001-5960-5782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109343769","display_name":"Kaixuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixuan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107377216","display_name":"Xinzhe Juan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinzhe Juan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072433926","display_name":"Ling Yang","orcid":"https://orcid.org/0000-0002-0751-5600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100707460","display_name":"Mengdi Wang","orcid":"https://orcid.org/0000-0002-2101-9507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengdi Wang","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":1.9965,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89146746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"22114","last_page":"22129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.2087000012397766,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.2087000012397766,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.14339999854564667,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.1137000024318695,"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/process","display_name":"Process (computing)","score":0.5532000064849854},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5067999958992004},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3034000098705292},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.2574000060558319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6078000068664551},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5516999959945679},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1205","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1205","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1205.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1205","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1205","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1205.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034029.pdf","grobid_xml":"https://content.openalex.org/works/W4416034029.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Verification":[0],"is":[1],"crucial":[2],"for":[3],"effective":[4],"mathematical":[5,47],"reasoning.We":[6],"present":[7],"a":[8,35],"new":[9],"temporal":[10],"consistency":[11,33],"method":[12,31,72,95],"where":[13],"verifiers":[14],"iteratively":[15],"refine":[16],"their":[17],"judgments":[18],"based":[19],"on":[20,87],"the":[21,65,89],"previous":[22],"assessment.Unlike":[23],"one-round":[24],"verification":[25,42],"or":[26],"multi-model":[27],"debate":[28],"approaches,":[29],"our":[30,71,94],"leverages":[32],"in":[34],"sequence":[36],"of":[37],"self-reflection":[38],"actions":[39],"to":[40,64,80,99],"improve":[41],"accuracy.Empirical":[43],"evaluations":[44],"across":[45],"diverse":[46],"process":[48],"error":[49],"identification":[50],"benchmarks":[51],"(Mathcheck,":[52],"ProcessBench,":[53],"and":[54,85],"PRM800K)":[55],"show":[56],"consistent":[57],"performance":[58,97],"improvements":[59],"over":[60],"baseline":[61],"methods.When":[62],"applied":[63],"recent":[66],"DeepSeek":[67],"R1":[68],"distilled":[69,78,90],"models,":[70],"demonstrates":[73],"strong":[74],"performance,":[75],"enabling":[76],"7B/8B":[77],"models":[79,84],"outperform":[81],"all":[82],"70B/72B":[83],"GPT-4o":[86],"ProcessBench.Notably,":[88],"14B":[91],"model":[92],"with":[93],"achieves":[96],"comparable":[98],"Deepseek-R1.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}