{"id":"https://openalex.org/W4414230891","doi":"https://doi.org/10.1109/sera65747.2025.11154515","title":"Automated Code Summarization by Training Large Language Models with Crowdsourced Knowledge","display_name":"Automated Code Summarization by Training Large Language Models with Crowdsourced Knowledge","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4414230891","doi":"https://doi.org/10.1109/sera65747.2025.11154515"},"language":"en","primary_location":{"id":"doi:10.1109/sera65747.2025.11154515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera65747.2025.11154515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACIS 23rd International Conference on Software Engineering Research, Management and Applications (SERA)","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/A5101641557","display_name":"Meng Xia","orcid":"https://orcid.org/0000-0001-6386-8497"},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Xia","raw_affiliation_strings":["University of Nebraska at Omaha,Computer Science,Nebraska,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nebraska at Omaha,Computer Science,Nebraska,USA","institution_ids":["https://openalex.org/I122266389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117495635","display_name":"Shradha Maharjan","orcid":null},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shradha Maharjan","raw_affiliation_strings":["University of Nebraska at Omaha,Computer Science,Nebraska,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nebraska at Omaha,Computer Science,Nebraska,USA","institution_ids":["https://openalex.org/I122266389"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035020782","display_name":"Myoungkyu Song","orcid":"https://orcid.org/0000-0003-4477-8933"},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Myoungkyu Song","raw_affiliation_strings":["University of Nebraska at Omaha,Computer Science,Nebraska,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nebraska at Omaha,Computer Science,Nebraska,USA","institution_ids":["https://openalex.org/I122266389"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I122266389"],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92968984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9965999722480774,"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/T10260","display_name":"Software Engineering Research","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7835999727249146},{"id":"https://openalex.org/keywords/program-comprehension","display_name":"Program comprehension","score":0.652899980545044},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5641999840736389},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5620999932289124},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.555899977684021},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.508899986743927},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44530001282691956},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.4341999888420105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238999843597412},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7835999727249146},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.652899980545044},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5641999840736389},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5620999932289124},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47450000047683716},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.44749999046325684},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44429999589920044},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.4341999888420105},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C81587897","wikidata":"https://www.wikidata.org/wiki/Q181702","display_name":"Software documentation","level":5,"score":0.357699990272522},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.35530000925064087},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.3009999990463257},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sera65747.2025.11154515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera65747.2025.11154515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACIS 23rd International Conference on Software Engineering Research, Management and Applications (SERA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1970407057","https://openalex.org/W1994683471","https://openalex.org/W2101105183","https://openalex.org/W2148469619","https://openalex.org/W2294980783","https://openalex.org/W2741561716","https://openalex.org/W2810627707","https://openalex.org/W2888557792","https://openalex.org/W2963541700","https://openalex.org/W2979271470","https://openalex.org/W3085939759","https://openalex.org/W3086449553","https://openalex.org/W3098605233","https://openalex.org/W3099640733","https://openalex.org/W3108032709","https://openalex.org/W3155146092","https://openalex.org/W3161997752","https://openalex.org/W3162689995","https://openalex.org/W3176740355","https://openalex.org/W3198685994","https://openalex.org/W4214548153","https://openalex.org/W4221166942","https://openalex.org/W4247854836","https://openalex.org/W4385187421","https://openalex.org/W4389518960","https://openalex.org/W4390667250","https://openalex.org/W4392414327","https://openalex.org/W4408047557"],"related_works":[],"abstract_inverted_index":{"In":[0,151],"modern":[1],"software":[2,13,65],"development,":[3],"efficient":[4],"program":[5,201],"comprehension":[6],"is":[7],"essential":[8,180],"for":[9,103,132],"maintaining":[10],"and":[11,31,76,100,128,144,163,186,194],"evolving":[12],"systems.":[14],"Developers":[15],"often":[16,68],"dedicate":[17],"over":[18,165],"$50":[19],"\\%$":[20],"of":[21,41,119,161,182],"their":[22],"time":[23,32],"to":[24,28,72,140,191],"understanding":[25],"code":[26,75,183,197],"due":[27],"the":[29,116,120,123],"complexity":[30],"demands":[33],"involved.":[34],"Code":[35],"summarization-generating":[36],"concise":[37],"natural":[38],"language":[39,98],"descriptions":[40],"source":[42],"code-has":[43],"emerged":[44],"as":[45,64],"a":[46,90,96,137],"potential":[47],"solution.":[48],"However,":[49],"existing":[50],"automated":[51,86],"summarization":[52],"techniques":[53],"frequently":[54],"produce":[55,192],"summaries":[56,112,198],"that":[57,88,113,199],"are":[58],"incomplete":[59],"or":[60],"lack":[61],"accuracy.":[62],"Moreover,":[63],"evolves,":[66],"documentation":[67],"becomes":[69],"outdated,":[70],"leading":[71],"discrepancies":[73],"between":[74],"comments.":[77],"To":[78],"address":[79],"these":[80],"challenges,":[81],"we":[82],"present":[83],"DeepKnowCode,":[84],"an":[85],"approach":[87,107],"utilizes":[89],"DEEP":[91],"learning":[92],"technique":[93],"based":[94],"on":[95],"large":[97],"model":[99],"crowdsourced":[101,176],"KNOWledge":[102],"CODE":[104],"summarization.":[105],"This":[106],"aids":[108],"developers":[109],"by":[110],"generating":[111],"elucidate":[114],"(1)":[115],"internal":[117],"behavior":[118],"code,":[121],"(2)":[122],"rationale":[124],"behind":[125],"its":[126,133,172,189],"implementation,":[127],"(3)":[129],"practical":[130],"guidelines":[131],"use.":[134],"We":[135],"implemented":[136],"research":[138],"prototype":[139],"assess":[141],"real-world":[142],"applicability":[143],"rigorously":[145],"evaluated":[146],"DeepKnowCode":[147,154,178],"against":[148],"state-of-the-art":[149],"approaches.":[150],"our":[152],"evaluation,":[153],"demonstrates":[155],"performance":[156],"improvements":[157],"in":[158],"BLEU":[159],"scores":[160],"38.8%":[162],"39.2%":[164],"two":[166],"baselines,":[167],"with":[168],"statistical":[169],"validation":[170],"underscoring":[171],"effectiveness.":[173],"By":[174],"incorporating":[175],"knowledge,":[177],"captures":[179],"elements":[181],"semantics,":[184],"context,":[185],"patterns,":[187],"enhancing":[188],"ability":[190],"accurate":[193],"contextually":[195],"relevant":[196],"facilitate":[200],"comprehension.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}