{"id":"https://openalex.org/W7140108392","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.70","title":"Don\u2019t Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","display_name":"Don\u2019t Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140108392","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.70"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.70","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.70","pdf_url":"https://aclanthology.org/2026.findings-eacl.70.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-eacl.70.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130409321","display_name":"Jiwon Moon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwon Moon","raw_affiliation_strings":["IPAI , Seoul National University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IPAI , Seoul National University ,","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114620113","display_name":"Yerin Hwang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yerin Hwang","raw_affiliation_strings":["IPAI , Seoul National University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IPAI , Seoul National University ,","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077348778","display_name":"Dongryeol Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongryeol Lee","raw_affiliation_strings":["Dept. of ECE , Seoul National University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of ECE , Seoul National University ,","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082023846","display_name":"Taegwan Kang","orcid":"https://orcid.org/0000-0002-9171-357X","observed_orcids":["https://orcid.org/0000-0002-9171-357X"]},"institutions":[{"id":"https://openalex.org/I4405258446","display_name":"LG AI Research (South Korea)","ror":"https://ror.org/00nt82y31","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210131320","https://openalex.org/I4405258446"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taegwan Kang","raw_affiliation_strings":["LG AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LG AI Research","institution_ids":["https://openalex.org/I4405258446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103104054","display_name":"Yongil Kim","orcid":"https://orcid.org/0000-0003-0458-5280","observed_orcids":["https://orcid.org/0000-0003-0458-5280"]},"institutions":[{"id":"https://openalex.org/I4405258446","display_name":"LG AI Research (South Korea)","ror":"https://ror.org/00nt82y31","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210131320","https://openalex.org/I4405258446"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongil Kim","raw_affiliation_strings":["LG AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LG AI Research","institution_ids":["https://openalex.org/I4405258446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077832834","display_name":"Kyomin Jung","orcid":"https://orcid.org/0000-0003-2547-7051","observed_orcids":["https://orcid.org/0000-0003-2547-7051"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyomin Jung","raw_affiliation_strings":["Dept. of ECE , Seoul National University ,","IPAI , Seoul National University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of ECE , Seoul National University ,","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"IPAI , Seoul National University ,","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":32.0444,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99512474,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1364","last_page":"1389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9570000171661377,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9570000171661377,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.01679999940097332,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10533","display_name":"Teaching and Learning Programming","score":0.011800000444054604,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.6769999861717224},{"id":"https://openalex.org/keywords/code-evaluation","display_name":"code evaluation","score":0.9070000052452087},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5950000286102295},{"id":"https://openalex.org/keywords/assessment-bias","display_name":"evaluation bias","score":0.6980000138282776},{"id":"https://openalex.org/keywords/program-correctness","display_name":"program correctness","score":0.4090000092983246},{"id":"https://openalex.org/keywords/variable-names","display_name":"variable names","score":0.42899999022483826},{"id":"https://openalex.org/keywords/code-formatting","display_name":"code formatting","score":0.7620000243186951},{"id":"https://openalex.org/keywords/test-case-generation","display_name":"test case generation","score":0.6520000100135803},{"id":"https://openalex.org/keywords/automated-code-evaluation","display_name":"automated code evaluation","score":0.3840000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212999820709229},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6205000281333923},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4226999878883362},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24619999527931213},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24220000207424164}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.70","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.70","pdf_url":"https://aclanthology.org/2026.findings-eacl.70.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.16222","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.16222","pdf_url":"https://arxiv.org/pdf/2505.16222","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.16222","doi":"https://doi.org/10.48550/arxiv.2505.16222","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.16222","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.70","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.70","pdf_url":"https://aclanthology.org/2026.findings-eacl.70.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8290584339","display_name":null,"funder_award_id":"IITP-2025-RS-2024-00437633","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140108392.pdf","grobid_xml":"https://content.openalex.org/works/W7140108392.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414742445","https://openalex.org/W7140488941","https://openalex.org/W7155073747","https://openalex.org/W4404782360","https://openalex.org/W4403661448","https://openalex.org/W7169494807","https://openalex.org/W4415272726","https://openalex.org/W4417530054","https://openalex.org/W7203980511","https://openalex.org/W7166851171"],"abstract_inverted_index":{"With":[0],"the":[1,22,86,159],"growing":[2],"use":[3],"of":[4,24,90,96],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"as":[9,62],"evaluators,":[10],"their":[11,104],"application":[12],"has":[13],"expanded":[14],"to":[15,126,146,152],"code":[16,26,53,58,100,164],"evaluation":[17,101,165],"tasks,":[18],"where":[19],"they":[20],"assess":[21],"correctness":[23],"generated":[25],"without":[27],"relying":[28],"on":[29,107],"reference":[30],"implementations.While":[31],"this":[32,91],"offers":[33],"scalability":[34],"and":[35,48,102,113,129],"flexibility,":[36],"it":[37],"also":[38],"raises":[39],"a":[40],"critical,":[41],"unresolved":[42],"question:":[43],"Can":[44],"LLM":[45,76,108,122,142],"judges":[46,77,123,143],"fairly":[47],"robustly":[49],"evaluate":[50],"semantically":[51],"equivalent":[52],"with":[54],"superficial":[55],"variations?Functionally":[56],"correct":[57],"often":[59],"exhibits":[60],"variations-such":[61],"differences":[63],"in":[64,99,133],"variable":[65],"names,":[66],"comments,":[67],"or":[68,135],"formatting-that":[69],"should":[70],"not":[71],"influence":[72],"its":[73],"correctness.Yet,":[74],"whether":[75],"can":[78],"reliably":[79],"handle":[80],"these":[81,147],"variations":[82],"remains":[83],"unclear.We":[84],"present":[85],"first":[87],"comprehensive":[88],"study":[89],"issue,":[92],"defining":[93],"six":[94],"types":[95],"potential":[97],"bias":[98],"revealing":[103],"systematic":[105],"impact":[106],"judges.Across":[109],"five":[110],"programming":[111],"languages":[112],"multiple":[114],"LLMs,":[115],"we":[116,139],"empirically":[117],"demonstrate":[118],"that":[119,141],"all":[120],"tested":[121],"are":[124],"susceptible":[125],"both":[127],"positive":[128],"negative":[130],"biases,":[131],"resulting":[132],"inflated":[134],"unfairly":[136],"low":[137],"scores.Moreover,":[138],"observe":[140],"remain":[144],"vulnerable":[145],"biases":[148],"even":[149],"when":[150],"prompted":[151],"generate":[153],"test":[154],"cases":[155],"before":[156],"scoring,":[157],"highlighting":[158],"need":[160],"for":[161],"more":[162],"robust":[163],"methods.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-10-21T09:56:26.102985","created_date":"2026-03-24T00:00:00"}