{"id":"https://openalex.org/W4402684151","doi":"https://doi.org/10.18653/v1/2024.acl-srw.6","title":"InstructCoder: Instruction Tuning Large Language Models for Code Editing","display_name":"InstructCoder: Instruction Tuning Large Language Models for Code Editing","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402684151","doi":"https://doi.org/10.18653/v1/2024.acl-srw.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.acl-srw.6","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-srw.6","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101812385","display_name":"Kaixin Li","orcid":"https://orcid.org/0000-0002-6931-4038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100941398","display_name":"Qisheng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qisheng Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102588838","display_name":"James Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334127","display_name":"Hui Chen","orcid":"https://orcid.org/0000-0001-5462-8029"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101498987","display_name":"Yuxi Xie","orcid":"https://orcid.org/0009-0009-0843-6507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxi Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021551649","display_name":"Tianyi Liu","orcid":"https://orcid.org/0000-0002-0912-7652"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiedong Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107453531","display_name":"Michael Shieh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Shieh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015879697","display_name":"Junxian He","orcid":"https://orcid.org/0009-0007-9559-6941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junxian He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88458485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.9771999716758728,"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"}},"topics":[{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.9771999716758728,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9236999750137329,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9189000129699707,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.815935492515564},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5779423117637634},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5594701170921326},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5058943629264832},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2730809450149536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815935492515564},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5779423117637634},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5594701170921326},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5058943629264832},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2730809450149536},{"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":2,"locations":[{"id":"doi:10.18653/v1/2024.acl-srw.6","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-srw.6","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-158752","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-158752","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Code":[0],"editing":[1,21,120],"encompasses":[2],"a":[3,59],"variety":[4],"of":[5,29,45,78,110,175],"pragmatic":[6],"tasks":[7,98,152],"that":[8,164],"developers":[9],"deal":[10],"with":[11,126],"daily.":[12],"Despite":[13],"its":[14],"relevance":[15],"and":[16,105,115,150],"practical":[17],"usefulness,":[18],"automatic":[19],"code":[20,52,93,103,106,119,176],"remains":[22],"an":[23,144],"underexplored":[24],"area":[25],"in":[26],"the":[27,43,74,83,138,173],"evolution":[28],"deep":[30],"learning":[31],"models,":[32],"partly":[33],"due":[34],"to":[35,50,72,88,155],"data":[36,129],"scarcity.":[37],"In":[38,76],"this":[39],"work,":[40],"we":[41,66,80],"explore":[42],"use":[44],"Large":[46],"Language":[47],"Models":[48],"(LLMs)":[49],"edit":[51],"based":[53],"on":[54,58,168],"user":[55],"instructions.":[56,75],"Evaluated":[57],"novel":[60],"human-written":[61],"execution-based":[62],"benchmark":[63],"dubbed":[64],"EditEval,":[65],"found":[67],"current":[68],"models":[69],"often":[70],"struggle":[71],"fulfill":[73],"light":[77],"this,":[79],"contribute":[81],"InstructCoder,":[82],"first":[84],"instruction-tuning":[85],"dataset":[86,139],"designed":[87],"adapt":[89],"LLMs":[90,166],"for":[91,158],"general-purpose":[92],"editing,":[94],"containing":[95],"high-diversity":[96],"code-editing":[97,180],"such":[99],"as":[100,135],"comment":[101],"insertion,":[102],"optimization,":[104],"refactoring.":[107],"It":[108],"consists":[109],"over":[111],"114,000":[112],"instruction-input-output":[113],"triplets":[114],"covers":[116],"multiple":[117],"distinct":[118],"scenarios.":[121],"The":[122],"collection":[123],"process":[124],"starts":[125],"filtered":[127],"commit":[128],"sourced":[130],"from":[131],"GitHub":[132],"Python":[133],"repositories":[134],"seeds.":[136],"Subsequently,":[137],"is":[140],"systematically":[141],"expanded":[142],"through":[143],"iterative":[145],"process,":[146],"where":[147],"both":[148],"seed":[149],"generated":[151],"are":[153],"used":[154],"prompt":[156],"ChatGPT":[157],"more":[159],"data.":[160],"Our":[161],"findings":[162],"reveal":[163],"open-source":[165],"fine-tuned":[167],"InstructCoder":[169],"can":[170],"significantly":[171],"enhance":[172],"accuracy":[174],"edits,":[177],"exhibiting":[178],"superior":[179],"performance":[181],"matching":[182],"advanced":[183],"proprietary":[184],"LLMs.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}