{"id":"https://openalex.org/W7126383469","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.148","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","display_name":"ICE-Score: Instructing Large Language Models to Evaluate Code","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126383469","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.148"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.148","pdf_url":"https://aclanthology.org/2024.findings-eacl.148.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: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.148.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124614304","display_name":"Terry Yue Zhuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Terry Yue Zhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5124614304"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.6465,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98512492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2232","last_page":"2242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.15690000355243683,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.15690000355243683,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.1315000057220459,"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":0.09950000047683716,"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/code","display_name":"Code (set theory)","score":0.5108000040054321},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.30070000886917114},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29409998655319214},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.2897999882698059},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2773999869823456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6811000108718872},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5108000040054321},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4535999894142151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.148","pdf_url":"https://aclanthology.org/2024.findings-eacl.148.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: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.148","pdf_url":"https://aclanthology.org/2024.findings-eacl.148.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: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6449708938598633,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126383469.pdf","grobid_xml":"https://content.openalex.org/works/W7126383469.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,30,40,80,95,203],"the":[3,11,19,121,137,145,196],"field":[4],"of":[5,13,21,50,123,147,177],"natural":[6],"language":[7,15,113],"generation":[8],"have":[9,26,73],"facilitated":[10],"use":[12],"large":[14,112],"models":[16,25,114],"to":[17,60,88,195],"assess":[18],"quality":[20],"generated":[22],"text.Although":[23],"these":[24,101],"shown":[27],"promising":[28],"results":[29,163],"tasks":[31,43,56],"such":[32,55,70],"as":[33,71],"machine":[34],"translation":[35],"and":[36,133,156,159,179,185,192],"summarization,":[37],"their":[38],"applicability":[39],"code":[41,81,117,172,205],"intelligence":[42,82,206],"remains":[44],"limited":[45],"without":[46,136],"human":[47,67,78,134],"involvement.The":[48],"complexity":[49],"programming":[51,161,183],"concepts":[52],"required":[53],"for":[54,116,139,171],"makes":[57],"it":[58],"difficult":[59],"develop":[61],"evaluation":[62,108,190],"metrics":[63,170],"that":[64,165],"align":[65],"with":[66,77,97,130],"judgment.Token-matching-based":[68],"metrics,":[69],"BLEU,":[72],"demonstrated":[74],"weak":[75],"correlations":[76,129],"practitioners":[79],"tasks.Moreover,":[83],"utilizing":[84],"human-written":[85],"test":[86,140],"suites":[87],"evaluate":[89,144],"functional":[90,131],"correctness":[91,132],"can":[92],"be":[93],"challenging":[94],"domains":[96],"low":[98],"resources.To":[99],"overcome":[100],"obstacles,":[102],"we":[103],"propose":[104],"ICE-Score,":[105],"a":[106],"new":[107],"metric":[109,119,149,167,191],"via":[110],"instructing":[111],"(LLMs)":[115],"assessments.Our":[118],"addresses":[120],"limitations":[122],"existing":[124],"approaches":[125],"by":[126],"achieving":[127],"superior":[128],"preferences,":[135],"need":[138],"oracles":[141],"or":[142],"references.We":[143],"efficacy":[146],"our":[148,166,189],"on":[150],"two":[151],"different":[152],"aspects":[153],"(human":[154],"preference":[155],"execution":[157],"success)":[158],"four":[160],"languages.Our":[162],"demonstrate":[164],"surpasses":[168],"state-ofthe-art":[169],"generation,":[173],"delivering":[174],"high":[175],"levels":[176],"accuracy":[178],"consistency":[180],"across":[181],"various":[182],"languages":[184],"tasks.We":[186],"also":[187],"make":[188],"datasets":[193],"available":[194],"public":[197],"1":[198],",":[199],"encouraging":[200],"further":[201],"research":[202],"evaluating":[204],"tasks.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2026-02-02T00:00:00"}