{"id":"https://openalex.org/W4416036086","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.94","title":"Evaluating Step-by-step Reasoning Traces: A Survey","display_name":"Evaluating Step-by-step Reasoning Traces: A Survey","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036086","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.94"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.94","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.94","pdf_url":"https://aclanthology.org/2025.findings-emnlp.94.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.94.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jinu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinu Lee","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120308992","display_name":"Julia Hockenmaier","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Hockenmaier","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":14.8573,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.98807131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1789","last_page":"1814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.2732999920845032,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.2732999920845032,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.1429000049829483,"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/T10028","display_name":"Topic Modeling","score":0.08590000122785568,"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/taxonomy","display_name":"Taxonomy (biology)","score":0.6119999885559082},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47760000824928284},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.4277999997138977},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.3822999894618988},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.37070000171661377},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.36329999566078186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931999921798706},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5461000204086304},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.4277999997138977},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26170000433921814}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.94","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.94","pdf_url":"https://aclanthology.org/2025.findings-emnlp.94.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.94","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.94","pdf_url":"https://aclanthology.org/2025.findings-emnlp.94.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036086.pdf","grobid_xml":"https://content.openalex.org/works/W4416036086.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Step-by-step":[0],"reasoning":[1,8,21,58],"is":[2,23],"widely":[3],"used":[4],"to":[5,88],"enhance":[6],"the":[7,18,76,104,107],"ability":[9],"of":[10,20,56,63,124],"large":[11],"language":[12],"models":[13],"(LLMs)":[14],"in":[15,38],"complex":[16],"problems.Evaluating":[17],"quality":[19],"traces":[22],"crucial":[24],"for":[25,91],"understanding":[26],"and":[27,44,73,84],"improving":[28],"LLM":[29,126],"reasoning.However,":[30],"existing":[31],"evaluation":[32,64],"practices":[33],"are":[34],"highly":[35],"inconsistent,":[36],"resulting":[37],"fragmented":[39],"progress":[40],"across":[41],"evaluator":[42,82,99,105,113],"design":[43],"benchmark":[45],"development.To":[46],"address":[47],"this":[48,50],"gap,":[49],"survey":[51],"provides":[52],"a":[53,61,115],"comprehensive":[54],"overview":[55],"step-by-step":[57],"evaluation,":[59],"proposing":[60],"taxonomy":[62],"criteria":[65],"with":[66],"four":[67],"toplevel":[68],"categories":[69],"(factuality,":[70],"validity,":[71],"coherence,":[72],"utility).Based":[74],"on":[75],"taxonomy,":[77],"we":[78],"review":[79],"different":[80],"datasets,":[81],"implementations,":[83],"recent":[85],"findings,":[86],"leading":[87],"promising":[89,109],"directions":[90],"future":[92],"research.":[93],"QueryTrace":[94],"2Trace":[95],"1Trace":[96],"3Meta-evaluation":[97],"benchmarks:Can":[98],"classify":[100],"good/bad":[101],"steps?Verifier-guided":[102],"search:Can":[103],"choose":[106],"most":[108],"trace?Reinforcement":[110],"learning:":[111],"Are":[112],"scores":[114],"good":[116],"reward":[117],"function?":[118],"Chosen":[119],"trace":[120],"answer:":[121],"Correct":[122],"Performance":[123],"trained":[125],"Classification":[127],"accuracy":[128]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-08T00:00:00"}