{"id":"https://openalex.org/W4411523084","doi":"https://doi.org/10.1145/3728947","title":"The First Prompt Counts the Most! An Evaluation of Large Language Models on Iterative Example-Based Code Generation","display_name":"The First Prompt Counts the Most! An Evaluation of Large Language Models on Iterative Example-Based Code Generation","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4411523084","doi":"https://doi.org/10.1145/3728947"},"language":"en","primary_location":{"id":"doi:10.1145/3728947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3728947","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM 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/A5100724082","display_name":"Yingjie Fu","orcid":"https://orcid.org/0000-0003-2574-9774"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjie Fu","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2574-9774","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062449586","display_name":"Bozhou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bozhou Li","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7519-5733","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101915882","display_name":"Linyi Li","orcid":"https://orcid.org/0000-0002-5403-3217"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Linyi Li","raw_affiliation_strings":["Simon Fraser University, Burnaby, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5403-3217","affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008772211","display_name":"Wentao Zhang","orcid":"https://orcid.org/0000-0002-7532-5550"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7532-5550","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048118068","display_name":"Tao Xie","orcid":"https://orcid.org/0000-0002-6731-216X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xie","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6731-216X","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.08,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96018234,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2","issue":"ISSTA","first_page":"1583","last_page":"1606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987999796867371,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9886000156402588,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6443236470222473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.633715808391571},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5927414298057556},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4957464635372162},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4910886287689209},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4852018654346466},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4801477789878845},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4670998454093933},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4076513946056366},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3344026207923889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2820553779602051},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.19220048189163208},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10745659470558167}],"concepts":[{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6443236470222473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.633715808391571},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5927414298057556},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4957464635372162},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4910886287689209},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4852018654346466},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4801477789878845},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4670998454093933},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4076513946056366},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3344026207923889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2820553779602051},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.19220048189163208},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10745659470558167},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3728947","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1964237346","https://openalex.org/W2096449544","https://openalex.org/W2110311336","https://openalex.org/W2114345296","https://openalex.org/W2120787570","https://openalex.org/W2144951274","https://openalex.org/W2159076953","https://openalex.org/W2160580192","https://openalex.org/W2537005436","https://openalex.org/W2551905807","https://openalex.org/W2587580284","https://openalex.org/W2972934903","https://openalex.org/W2975599812","https://openalex.org/W2990579602","https://openalex.org/W3014415287","https://openalex.org/W3014581084","https://openalex.org/W3033423882","https://openalex.org/W3135873378","https://openalex.org/W3161457214","https://openalex.org/W3177813494","https://openalex.org/W3193990408","https://openalex.org/W4220852596","https://openalex.org/W4226485558","https://openalex.org/W4234542549","https://openalex.org/W4234895808","https://openalex.org/W4237412827","https://openalex.org/W4283210053","https://openalex.org/W4283706798","https://openalex.org/W4287024925","https://openalex.org/W4287755201","https://openalex.org/W4292779060","https://openalex.org/W4298144617","https://openalex.org/W4300989059","https://openalex.org/W4304194220","https://openalex.org/W4309804142","https://openalex.org/W4311887664","https://openalex.org/W4320559222","https://openalex.org/W4320814215","https://openalex.org/W4321277276","https://openalex.org/W4327810158","https://openalex.org/W4360834937","https://openalex.org/W4366197117","https://openalex.org/W4367860052","https://openalex.org/W4375869868","https://openalex.org/W4379537200","https://openalex.org/W4379548473","https://openalex.org/W4383605161","https://openalex.org/W4384026527","https://openalex.org/W4384918448","https://openalex.org/W4385849242","https://openalex.org/W4385902209","https://openalex.org/W4386185625","https://openalex.org/W4387561453","https://openalex.org/W4390215418","https://openalex.org/W4391272793","https://openalex.org/W4391833048","https://openalex.org/W4392822465","https://openalex.org/W4393035110","https://openalex.org/W4396219010","https://openalex.org/W4396815229","https://openalex.org/W4399357038","https://openalex.org/W4399694963","https://openalex.org/W4399795128","https://openalex.org/W4401306886","https://openalex.org/W4401306979","https://openalex.org/W6967084484"],"related_works":["https://openalex.org/W2955859849","https://openalex.org/W2152921782","https://openalex.org/W382594479","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2151245229","https://openalex.org/W199086061","https://openalex.org/W2140902089","https://openalex.org/W1510553545","https://openalex.org/W3020827637"],"abstract_inverted_index":{"The":[0,188],"capabilities":[1],"of":[2,128,141,178,229,239,276,295],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"in":[7,96,235],"code":[8,60,66,98,116,143,150,158,214,309],"generation":[9,99,117,144,215],"have":[10],"been":[11],"extensively":[12],"studied,":[13],"particularly":[14],"for":[15,51,218,287,306],"implementing":[16,54],"target":[17,56,81,163,181],"functionalities":[18,82,164,182,232],"from":[19,61,83,165,184],"natural-language":[20],"descriptions.":[21],"As":[22],"an":[23,32,133],"alternative":[24],"to":[25,38,74,79,87,152,247],"natural":[26,202,266],"language,":[27,203],"input-output":[28],"(I/O)":[29],"examples":[30,63,155,199,260,279],"provide":[31],"accessible,":[33],"unambiguous,":[34],"and":[35,46,53,86,137,156,186,264,273,300,304],"flexible":[36],"way":[37],"describe":[39],"functionalities.":[40],"However,":[41,91],"their":[42],"inherent":[43],"diversity,":[44],"opaqueness,":[45],"incompleteness":[47,127],"impose":[48],"greater":[49],"challenges":[50],"understanding":[52],"the":[55,110,122,126,139,153,162,204,219,223,236,240,244,250,274,283,293],"requirements.":[57,90,253],"Therefore,":[58],"generating":[59,149,157],"I/O":[62,129,198,259,278],"(i.e.,":[64],"example-based":[65,97,115,142,213],"generation)":[67],"provides":[68],"a":[69,175],"new":[70,176],"perspective,":[71],"allowing":[72],"us":[73],"additionally":[75],"evaluate":[76],"LLMs\u2019":[77,205],"capability":[78],"infer":[80],"limited":[84],"information":[85],"process":[88],"new-form":[89],"related":[92],"research":[93],"about":[94],"LLMs":[95,173,245],"remains":[100,216],"largely":[101],"unexplored.":[102],"To":[103,120],"fill":[104],"this":[105,107],"gap,":[106],"paper":[108],"presents":[109],"first":[111,237],"comprehensive":[112],"study":[113],"on":[114],"using":[118,174,196],"LLMs.":[119,221],"address":[121],"incorrectness":[123],"caused":[124],"by":[125,208],"examples,":[130],"we":[131,255],"adopt":[132],"iterative":[134,197],"evaluation":[135],"framework":[136],"formalize":[138],"objective":[140],"as":[145],"two":[146],"sequential":[147],"sub-objectives:":[148],"conforming":[151],"given":[154,167],"that":[159,191,212,243,257],"successfully":[160,230],"implements":[161],"(iteratively)":[166],"examples.":[168],"We":[169],"assess":[170],"six":[171],"state-of-the-art":[172],"benchmark":[177],"172":[179],"diverse":[180],"(derived":[183],"HumanEval":[185],"CodeHunt).":[187],"results":[189],"demonstrate":[190],"when":[192],"requirements":[193],"are":[194,233],"described":[195],"rather":[200],"than":[201],"score":[206],"decreases":[207],"over":[209,227],"60%,":[210],"indicating":[211],"challenging":[217],"evaluated":[220],"Notably,":[222],"vast":[224],"majority":[225],"(even":[226],"95%)":[228],"implemented":[231],"achieved":[234],"round":[238],"iterations,":[241],"suggesting":[242,285],"struggle":[246],"effectively":[248],"utilize":[249],"iteratively":[251],"supplemented":[252],"Furthermore,":[254],"find":[256],"combining":[258],"with":[261],"even":[262],"imprecise":[263],"fragmental":[265],"language":[267],"descriptions":[268],"greatly":[269],"improves":[270],"LLM":[271],"performance,":[272],"selection":[275],"initial":[277],"can":[280],"also":[281],"influence":[282],"score,":[284],"opportunities":[286],"prompt":[288],"optimization.":[289],"These":[290],"findings":[291],"highlight":[292],"importance":[294],"early":[296],"prompts":[297],"during":[298],"interactions":[299],"offer":[301],"critical":[302],"insights":[303],"implications":[305],"enhancing":[307],"LLM-based":[308],"generation.":[310]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}