{"id":"https://openalex.org/W4410361283","doi":"https://doi.org/10.1145/3735636","title":"Less Is More: DocString Compression in Code Generation","display_name":"Less Is More: DocString Compression in Code Generation","publication_year":2025,"publication_date":"2025-05-14","ids":{"openalex":"https://openalex.org/W4410361283","doi":"https://doi.org/10.1145/3735636"},"language":"en","primary_location":{"id":"doi:10.1145/3735636","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735636","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"ACM Transactions on Software Engineering and Methodology","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/A5003840863","display_name":"Guang Yang","orcid":"https://orcid.org/0000-0002-3374-6680"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Yang","raw_affiliation_strings":["College of Computer Science and Technology/College of Artificial Intelligence/College of Software, Nanjing University of Aeronautics and Astronautics, Nanjing, China","Nanjing University of Aeronautics and Astronautics, China"],"raw_orcid":"https://orcid.org/0000-0002-3374-6680","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology/College of Artificial Intelligence/College of Software, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038150414","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-3723-7584"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China","Nanjing University of Aeronautics and Astronautics, China"],"raw_orcid":"https://orcid.org/0000-0002-3723-7584","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110686990","display_name":"Wei Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Cheng","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China","Nanjing University of Aeronautics and Astronautics, China"],"raw_orcid":"https://orcid.org/0009-0007-9418-5753","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115028456","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0009-0000-6271-746X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China","Nanjing University of Aeronautics and Astronautics, China"],"raw_orcid":"https://orcid.org/0009-0000-6271-746X","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441911","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0002-1180-3891"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["Nantong University, Nantong, China","Nantong University, China"],"raw_orcid":"https://orcid.org/0000-0002-1180-3891","affiliations":[{"raw_affiliation_string":"Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]},{"raw_affiliation_string":"Nantong University, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082624117","display_name":"Terry Yue Zhuo","orcid":"https://orcid.org/0000-0002-5760-5188"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Terry Yue Zhuo","raw_affiliation_strings":["Monash University, Clayton, Australia","Monash University, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5760-5188","affiliations":[{"raw_affiliation_string":"Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349854","display_name":"Ke Liu","orcid":"https://orcid.org/0000-0002-5224-1485"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Liu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China","National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-5224-1485","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424233","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0002-4558-0622"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore","Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4558-0622","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081036622","display_name":"David Lo","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Lo","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore","Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4367-7201","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030747944","display_name":"Taolue Chen","orcid":"https://orcid.org/0000-0002-5993-1665"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Taolue Chen","raw_affiliation_strings":["Birkbeck University of London, London, United Kingdom of Great Britain and Northern Ireland","Birkbeck, University of London, UK"],"raw_orcid":"https://orcid.org/0000-0002-5993-1665","affiliations":[{"raw_affiliation_string":"Birkbeck University of London, London, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I98259816"]},{"raw_affiliation_string":"Birkbeck, University of London, UK","institution_ids":["https://openalex.org/I98259816"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9231,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92533987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"35","issue":"2","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9975000023841858,"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/T10260","display_name":"Software Engineering Research","score":0.9965000152587891,"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/T10126","display_name":"Logic, programming, and type systems","score":0.9869999885559082,"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":0.7492590546607971},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4368254542350769},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.41063326597213745},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3262961804866791},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07343894243240356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492590546607971},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4368254542350769},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.41063326597213745},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3262961804866791},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07343894243240356},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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:10.1145/3735636","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735636","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6670970210","display_name":null,"funder_award_id":"62372232","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":20,"referenced_works":["https://openalex.org/W2774772126","https://openalex.org/W2997847174","https://openalex.org/W4295884601","https://openalex.org/W4385562549","https://openalex.org/W4386566536","https://openalex.org/W4387321091","https://openalex.org/W4387869031","https://openalex.org/W4389519226","https://openalex.org/W4389523718","https://openalex.org/W4392806399","https://openalex.org/W4394745423","https://openalex.org/W4394769034","https://openalex.org/W4399397061","https://openalex.org/W4399577572","https://openalex.org/W4400484392","https://openalex.org/W4400484905","https://openalex.org/W4401635661","https://openalex.org/W4402410226","https://openalex.org/W4402457350","https://openalex.org/W4402670850"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,163],"widespread":[1],"use":[2],"of":[3,152,165,182],"Large":[4],"Language":[5,71],"Models":[6],"(LLMs)":[7],"in":[8,62,69],"software":[9],"engineering":[10],"has":[11],"intensified":[12],"the":[13,45,52,87,150,174,180,183],"need":[14],"for":[15,23,44,54,119],"improved":[16],"model":[17],"and":[18,34,47,137,172],"resource":[19],"efficiency.":[20],"In":[21,105],"particular,":[22],"neural":[24],"code":[25,46,78,120,126],"generation,":[26],"LLMs":[27,132],"are":[28,48],"used":[29,50],"to":[30,36,77,116,134,169],"translate":[31],"function/method":[32],"signature":[33],"DocString":[35,117],"executable":[37],"code.":[38],"DocStrings,":[39],"which":[40],"capture":[41],"user":[42],"requirements":[43],"typically":[49],"as":[51,97],"prompt":[53,63,89],"LLMs,":[55],"often":[56],"contain":[57],"redundant":[58],"information.":[59],"Recent":[60],"advancements":[61],"compression":[64,90,112,118,147,161],"have":[65],"shown":[66],"promising":[67],"results":[68],"Natural":[70],"Processing":[72],"(NLP),":[73],"but":[74],"their":[75],"applicability":[76],"generation":[79,127],"remains":[80],"uncertain.":[81],"Our":[82,122],"empirical":[83],"study":[84],"shows":[85],"that":[86,143],"state-of-the-art":[88],"methods":[91,158],"achieve":[92],"only":[93],"about":[94],"10%":[95],"reduction,":[96],"further":[98],"reductions":[99],"would":[100],"cause":[101],"significant":[102],"performance":[103],"degradation.":[104],"our":[106],"study,":[107],"we":[108],"propose":[109],"a":[110],"novel":[111],"method,":[113],"ShortenDoc,":[114],"dedicated":[115],"generation.":[121],"experiments":[123],"on":[124],"six":[125],"datasets,":[128],"five":[129],"open":[130],"source":[131],"(1B":[133],"10B":[135],"parameters),":[136],"one":[138],"closed-source":[139],"LLM":[140],"GPT-4o":[141],"confirm":[142],"ShortenDoc":[144],"achieves":[145],"25\u201340%":[146],"while":[148,178],"preserving":[149],"quality":[151,181],"generated":[153,184],"code,":[154,185],"outperforming":[155],"other":[156],"baseline":[157],"at":[159],"similar":[160],"levels.":[162],"benefit":[164],"this":[166],"method":[167],"is":[168],"improve":[170],"efficiency":[171],"reduce":[173],"token":[175],"processing":[176],"cost":[177],"maintaining":[179],"especially":[186],"when":[187],"calling":[188],"third-party":[189],"APIs.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
