{"id":"https://openalex.org/W4400582875","doi":"https://doi.org/10.1145/3660769","title":"SimLLM: Calculating Semantic Similarity in Code Summaries using a Large Language Model-Based Approach","display_name":"SimLLM: Calculating Semantic Similarity in Code Summaries using a Large Language Model-Based Approach","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400582875","doi":"https://doi.org/10.1145/3660769"},"language":"en","primary_location":{"id":"doi:10.1145/3660769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660769","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3660769","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100641343","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-6525-2821"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Jin","raw_affiliation_strings":["The Ohio State University, Columbus, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026864098","display_name":"Zhiqiang Lin","orcid":"https://orcid.org/0000-0001-6527-5994"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqiang Lin","raw_affiliation_strings":["The Ohio State University, Columbus, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100641343"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.049,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88459029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"1","issue":"FSE","first_page":"1376","last_page":"1399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9973000288009644,"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":0.7386839985847473},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5618863105773926},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5411419868469238},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.528315007686615},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5279682874679565},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5079067349433899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36659127473831177},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33955490589141846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386839985847473},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5618863105773926},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5411419868469238},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.528315007686615},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5279682874679565},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5079067349433899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36659127473831177},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33955490589141846},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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:10.1145/3660769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660769","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":{"id":"doi:10.1145/3660769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660769","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3254667246","display_name":null,"funder_award_id":"N6600120C4020","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G3318334062","display_name":null,"funder_award_id":"CNS-2112471","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7568287664","display_name":null,"funder_award_id":"W911NF2110081","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1614298861","https://openalex.org/W1721182246","https://openalex.org/W2024932032","https://openalex.org/W2034209539","https://openalex.org/W2133333349","https://openalex.org/W2600463316","https://openalex.org/W2740887992","https://openalex.org/W2759181158","https://openalex.org/W2766839578","https://openalex.org/W2773532513","https://openalex.org/W2790235966","https://openalex.org/W2794557536","https://openalex.org/W2802734970","https://openalex.org/W2896457183","https://openalex.org/W2936695845","https://openalex.org/W2964121744","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2995435108","https://openalex.org/W3003257820","https://openalex.org/W3008088841","https://openalex.org/W3016473712","https://openalex.org/W3042185737","https://openalex.org/W3086007799","https://openalex.org/W3134616970","https://openalex.org/W3153414861","https://openalex.org/W3195727321","https://openalex.org/W3212375327","https://openalex.org/W4206238894","https://openalex.org/W4226037466","https://openalex.org/W4226271314","https://openalex.org/W4226327346","https://openalex.org/W4239584046","https://openalex.org/W4288253152","https://openalex.org/W4288375693","https://openalex.org/W4288400010","https://openalex.org/W4288601300","https://openalex.org/W4291186635","https://openalex.org/W4297819591","https://openalex.org/W4299311013","https://openalex.org/W4300113433","https://openalex.org/W4303684020","https://openalex.org/W4308632257","https://openalex.org/W4308641647","https://openalex.org/W4308731473","https://openalex.org/W4310428868","https://openalex.org/W4313185449","https://openalex.org/W4320830156","https://openalex.org/W4360818975","https://openalex.org/W4377864824","https://openalex.org/W4384155757","https://openalex.org/W4384918448","https://openalex.org/W4385899890","https://openalex.org/W4386185625","https://openalex.org/W4387250125","https://openalex.org/W4389364446","https://openalex.org/W4389911182","https://openalex.org/W4391940723","https://openalex.org/W4392481868","https://openalex.org/W4394638297","https://openalex.org/W6930396930"],"related_works":["https://openalex.org/W4376653378","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349","https://openalex.org/W2898077673","https://openalex.org/W4385239468","https://openalex.org/W4200476258","https://openalex.org/W2022470916","https://openalex.org/W3002840018"],"abstract_inverted_index":{"Code":[0],"summaries":[1,59],"are":[2,61],"pivotal":[3],"in":[4,18,58,64,71],"software":[5],"engineering,":[6],"serving":[7],"to":[8,51,86],"improve":[9],"code":[10,29,72,94],"readability,":[11],"maintainability,":[12],"and":[13,40,68,109],"collaboration.":[14],"While":[15],"recent":[16],"advancements":[17],"Large":[19],"Language":[20],"Models":[21],"(LLMs)":[22],"have":[23,42],"opened":[24],"new":[25],"avenues":[26],"for":[27,33],"automatic":[28],"summarization,":[30],"existing":[31,47,121,133],"metrics":[32,48,134],"evaluating":[34],"summary":[35],"quality,":[36],"such":[37],"as":[38],"BLEU":[39],"BERTScore,":[41],"notable":[43],"limitations.":[44],"Specifically,":[45],"these":[46],"either":[49],"fail":[50],"capture":[52],"the":[53,90,118],"nuances":[54],"of":[55,93,120],"semantic":[56,91],"meaning":[57],"or":[60],"further":[62],"limited":[63],"understanding":[65],"domain-specific":[66],"terminologies":[67],"expressions":[69],"prevalent":[70],"summaries.":[73,95],"In":[74],"this":[75],"paper,":[76],"we":[77],"present":[78],"Sim":[79,115,128],"LLM,":[80],"a":[81,102,110,138],"novel":[82],"LLM-based":[83],"approach":[84],"designed":[85],"more":[87],"precisely":[88],"evaluate":[89],"similarity":[92,113],"Built":[96],"upon":[97],"an":[98],"autoregressive":[99],"LLM":[100,116,129],"using":[101],"specialized":[103],"pretraining":[104],"task":[105],"on":[106],"permutated":[107],"inputs":[108],"pooling-based":[111],"pairwise":[112],"measure,":[114],"overcomes":[117],"shortcomings":[119],"metrics.":[122],"Our":[123],"empirical":[124],"evaluations":[125],"demonstrate":[126],"that":[127],"not":[130],"only":[131],"outperforms":[132],"but":[135],"also":[136],"shows":[137],"significantly":[139],"high":[140],"correlation":[141],"with":[142],"human":[143],"ratings.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}