{"id":"https://openalex.org/W4413967102","doi":"https://doi.org/10.1109/tse.2025.3605768","title":"Post-Incorporating Code Structural Knowledge Into Pretrained Models via ICL for Code Translation","display_name":"Post-Incorporating Code Structural Knowledge Into Pretrained Models via ICL for Code Translation","publication_year":2025,"publication_date":"2025-09-03","ids":{"openalex":"https://openalex.org/W4413967102","doi":"https://doi.org/10.1109/tse.2025.3605768"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2025.3605768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2025.3605768","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.22776","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yali Du","orcid":"https://orcid.org/0000-0001-7759-3906"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yali Du","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7759-3906","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hui Sun","orcid":"https://orcid.org/0000-0002-4701-5379"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Sun","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4701-5379","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ming Li","orcid":"https://orcid.org/0000-0001-7977-5500"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7977-5500","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11309735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":"11","first_page":"3038","last_page":"3055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9807999730110168,"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/T12031","display_name":"Speech and dialogue systems","score":0.9456999897956848,"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/computer-science","display_name":"Computer science","score":0.8557624816894531},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6643946170806885},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6333827972412109},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5721027851104736},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5646890997886658},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.42126280069351196},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4164109528064728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37529945373535156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36094385385513306},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14283519983291626},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.14178207516670227},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09072607755661011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8557624816894531},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6643946170806885},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6333827972412109},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5721027851104736},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5646890997886658},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.42126280069351196},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4164109528064728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37529945373535156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36094385385513306},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14283519983291626},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.14178207516670227},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09072607755661011},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tse.2025.3605768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2025.3605768","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"},{"id":"pmh:oai:arXiv.org:2503.22776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.22776","pdf_url":"https://arxiv.org/pdf/2503.22776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.22776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.22776","pdf_url":"https://arxiv.org/pdf/2503.22776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G242381732","display_name":null,"funder_award_id":"62076121","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2962780935","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2163672025","https://openalex.org/W2048831961","https://openalex.org/W1606349578","https://openalex.org/W4399567378"],"abstract_inverted_index":{"Code":[0,218],"translation":[1,211],"migrates":[2],"codebases":[3],"across":[4],"programming":[5],"languages.":[6],"Recently,":[7],"large":[8],"language":[9],"models":[10],"(LLMs)":[11],"have":[12],"achieved":[13],"significant":[14],"advancements":[15],"in":[16,75,175,209],"software":[17],"mining.":[18],"However,":[19],"handling":[20],"the":[21,60,106,138,182,247,254],"syntactic":[22,260],"structure":[23],"of":[24,108,118,129,249,256],"source":[25,131],"code":[26,65,132,190,210,250,259],"remains":[27],"a":[28,114,150,158,168],"challenge.":[29],"Classic":[30],"syntax-aware":[31],"methods":[32,97],"depend":[33],"on":[34,86,99],"intricate":[35],"model":[36,238],"architectures":[37],"and":[38,92,102,133,145,185,212],"loss":[39],"functions,":[40],"rendering":[41],"their":[42],"integration":[43],"into":[44,59,68,193,225],"LLM":[45],"training":[46,241],"resource-intensive.":[47],"This":[48],"paper":[49],"employs":[50],"in-context":[51],"learning":[52],"(ICL),":[53],"which":[54,165],"directly":[55],"integrates":[56],"task":[57],"exemplars":[58],"input":[61],"context,":[62],"to":[63,188,246],"post-incorporate":[64,189],"structural":[66,191,219,251],"knowledge":[67,192,220],"pre-trained":[69,226],"LLMs.":[70],"We":[71],"revisit":[72],"exemplar":[73,143],"selection":[74,84,144],"ICL":[76],"from":[77],"an":[78],"information-theoretic":[79],"perspective,":[80],"proposing":[81],"that":[82,147,202],"list-wise":[83],"based":[85,98],"information":[87,110],"coverage":[88,126],"is":[89,149,181],"more":[90],"precise":[91],"general":[93],"objective":[94],"than":[95],"traditional":[96],"combine":[100],"similarity":[101],"diversity.":[103],"To":[104],"address":[105],"challenges":[107],"quantifying":[109],"coverage,":[111],"we":[112,136,156],"introduce":[113],"surrogate":[115],"measure,":[116],"Coverage":[117],"Abstract":[119],"Syntax":[120],"Tree":[121],"(CAST),":[122],"measuring":[123],"maximum":[124],"subtree":[125],"between":[127],"ASTs":[128],"test":[130,197],"exemplars.":[134],"Furthermore,":[135],"formulate":[137],"NP-hard":[139],"CAST":[140,162],"maximization":[141,153],"for":[142,161],"prove":[146],"it":[148],"standard":[151],"submodular":[152,163],"problem.":[154],"Therefore,":[155],"propose":[157],"greedy":[159],"algorithm":[160],"maximization,":[164],"theoretically":[166],"guarantees":[167],"(1":[169],"\u2212":[170],"1/<italic":[171],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e</i>)-approximate":[173],"solution":[174],"polynomial":[176],"time":[177],"complexity.":[178],"Our":[179],"method":[180,204],"first":[183],"training-free":[184],"model-agnostic":[186],"approach":[187],"existing":[194],"LLMs":[195,207,227],"at":[196],"time.":[198],"Experimental":[199],"results":[200],"show":[201],"our":[203],"significantly":[205],"improves":[206],"performance":[208],"reveals":[213],"two":[214],"meaningful":[215],"insights:":[216],"1)":[217],"can":[221],"be":[222],"effectively":[223],"post-incorporated":[224],"during":[228,233],"inference,":[229],"despite":[230],"being":[231],"overlooked":[232],"training;":[234],"2)":[235],"Scaling":[236],"up":[237],"size":[239],"or":[240],"data":[242],"does":[243],"not":[244],"lead":[245],"emergence":[248],"knowledge,":[252],"underscoring":[253],"necessity":[255],"explicitly":[257],"considering":[258],"structure.":[261]},"counts_by_year":[],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}