{"id":"https://openalex.org/W7140115481","doi":"https://doi.org/10.1109/tse.2026.3676295","title":"Are They All Good? Evaluating the Quality of CoTs in LLM-Based Code Generation","display_name":"Are They All Good? Evaluating the Quality of CoTs in LLM-Based Code Generation","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140115481","doi":"https://doi.org/10.1109/tse.2026.3676295"},"language":null,"primary_location":{"id":"doi:10.1109/tse.2026.3676295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2026.3676295","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-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/A5052719394","display_name":"Binquan Zhang","orcid":"https://orcid.org/0000-0002-6468-9842"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binquan Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University"],"raw_orcid":"https://orcid.org/0000-0002-6468-9842","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114585361","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0002-2258-5893"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University"],"raw_orcid":"https://orcid.org/0000-0002-2258-5893","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130334530","display_name":"Zhiwen Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Luo","raw_affiliation_strings":["Beihang University"],"raw_orcid":"https://orcid.org/0009-0009-2009-5637","affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130341130","display_name":"Yuxin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Du","raw_affiliation_strings":["Beihang University"],"raw_orcid":"https://orcid.org/0009-0005-4356-8258","affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130348416","display_name":"Fang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University"],"raw_orcid":"https://orcid.org/0000-0002-3905-8133","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130363081","display_name":"Song Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Song Wang","raw_affiliation_strings":["York University"],"raw_orcid":"https://orcid.org/0000-0003-0531-5717","affiliations":[{"raw_affiliation_string":"York University","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130395073","display_name":"Lin Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Shi","raw_affiliation_strings":["Beihang University"],"raw_orcid":"https://orcid.org/0000-0003-1476-7213","affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":7.0482,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95785549,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"52","issue":"6","first_page":"1928","last_page":"1943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.08209999650716782,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08209999650716782,"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/T10260","display_name":"Software Engineering Research","score":0.07190000265836716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.0658000037074089,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/code-generation","display_name":"Code generation","score":0.5799999833106995},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5256999731063843},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4973999857902527},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3628999888896942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133999705314636},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5799999833106995},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5256999731063843},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4973999857902527},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.45570001006126404},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2854999899864197},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2026.3676295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2026.3676295","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4618028402328491,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G2870236305","display_name":null,"funder_award_id":"2024YFB3311503","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5717671410","display_name":null,"funder_award_id":"62272445","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2150884987","https://openalex.org/W4225108562","https://openalex.org/W4320814215","https://openalex.org/W4324138978","https://openalex.org/W4384026634","https://openalex.org/W4385571157","https://openalex.org/W4386982649","https://openalex.org/W4389520747","https://openalex.org/W4389523991","https://openalex.org/W4391282616","https://openalex.org/W4391841626","https://openalex.org/W4391876619","https://openalex.org/W4392384650","https://openalex.org/W4395029328","https://openalex.org/W4399601909","https://openalex.org/W4400582230","https://openalex.org/W4401996408","https://openalex.org/W4402442868","https://openalex.org/W4402670352","https://openalex.org/W4402671355","https://openalex.org/W4404782209","https://openalex.org/W4407551092","https://openalex.org/W4411119596","https://openalex.org/W4411449940","https://openalex.org/W4412945594","https://openalex.org/W4414281281","https://openalex.org/W4415746063","https://openalex.org/W7133209886","https://openalex.org/W7133224126","https://openalex.org/W7133231369"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"impressive":[6],"performance":[7,125],"in":[8,35,273],"code":[9,37,108,114,123,195,224,275,291],"generation,":[10,276],"particularly":[11],"when":[12,222,253],"augmented":[13],"with":[14],"chain-of-thought":[15],"(CoT)":[16],"prompting":[17,137],"techniques.":[18],"They":[19],"break":[20],"down":[21],"requirements":[22,160],"into":[23],"intermediate":[24],"reasoning":[25,284],"steps,":[26],"which":[27],"act":[28],"as":[29],"design":[30],"rationales":[31],"to":[32,173,203,206,210],"guide":[33],"LLMs":[34,70,100,204,248],"writing":[36],"like":[38],"human":[39],"programmers.":[40],"Thus,":[41],"the":[42,51,56,60,64,80,93,133,142,147,184,193,215,223,233,243,264,269,283,287],"quality":[43,65],"of":[44,55,66,98,163,183,192,271,290],"these":[45],"steps":[46],"is":[47,200,225,228],"crucial":[48],"for":[49,155,280],"ensuring":[50],"correctness":[52],"and":[53,95,131,161,177,214,286],"reliability":[54,289],"generated":[57,68,82,194],"code.":[58,216],"However,":[59],"specific":[61],"factors":[62,97,148,153,167],"influencing":[63],"CoT":[67,150,176,188,213,234,256,272],"by":[69,83,104,126,136,180],"remain":[71],"largely":[72],"unexplored.":[73],"To":[74],"what":[75],"extent":[76],"can":[77,249],"we":[78,218],"trust":[79],"thoughts":[81],"LLMs?":[84],"How":[85],"good":[86],"are":[87],"they?":[88],"This":[89,199],"paper":[90],"empirically":[91],"explores":[92],"external":[94,152],"internal":[96],"why":[99],"generate":[101],"unsatisfactory":[102],"CoTs":[103,135,245],"analyzing":[105,127],"1,023":[106],"failed":[107],"samples":[109],"on":[110,122,241,263],"two":[111],"widely":[112],"used":[113],"generation":[115,124],"benchmarks.":[116],"We":[117],"also":[118],"evaluate":[119],"their":[120],"impact":[121],"210":[128],"CoT-code":[129],"pairs":[130],"refining":[132,242],"unsatisfied":[134],"LLMs.":[138],"Our":[139,238,259],"study":[140],"yields":[141],"following":[143],"findings:":[144],"1)":[145],"Among":[146],"affecting":[149],"quality,":[151],"account":[154],"53.60%,":[156],"primarily":[157,201],"including":[158],"unclear":[159],"lack":[162],"contextual":[164],"information.":[165,258],"Internal":[166],"make":[168],"up":[169],"40.10%,":[170],"mainly":[171],"due":[172,202],"inconsistencies":[174,211],"between":[175,212],"prompts":[178],"caused":[179],"LLMs\u2019":[181],"misunderstanding":[182],"instructions.":[185],"2)":[186],"Despite":[187],"being":[189],"correct,":[190,226],"18.5%":[191],"still":[196],"contains":[197,235],"errors.":[198,236],"failing":[205],"follow":[207],"instructions,":[208],"leading":[209],"Additionally,":[217],"found":[219],"that":[220,232,247,267],"even":[221],"there":[227],"an":[229],"11.90%":[230],"chance":[231],"3)":[237],"further":[239],"research":[240],"low-quality":[244],"reveals":[246],"improve":[250],"CoT,":[251],"especially":[252],"providing":[254],"detailed":[255],"problem":[257],"findings":[260],"shed":[261],"light":[262],"underlying":[265],"issues":[266],"hinder":[268],"effectiveness":[270],"LLM-based":[274],"offering":[277],"valuable":[278],"insights":[279],"enhancing":[281],"both":[282],"process":[285],"overall":[288],"generation.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-03-24T00:00:00"}
