{"id":"https://openalex.org/W4412703863","doi":"https://doi.org/10.1145/3696630.3728510","title":"Enhancing Code LLM Training with Programmer Attention","display_name":"Enhancing Code LLM Training with Programmer Attention","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4412703863","doi":"https://doi.org/10.1145/3696630.3728510"},"language":"en","primary_location":{"id":"doi:10.1145/3696630.3728510","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728510","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696630.3728510","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696630.3728510","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100376917","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0001-5719-772X"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["Department of Computer Science, Vanderbilt University, Nashville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0001-5719-772X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032644660","display_name":"Chen Huang","orcid":"https://orcid.org/0000-0002-3542-7085"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Huang","raw_affiliation_strings":["Department of Computer Science, Sichuan University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-3542-7085","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Sichuan University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057662526","display_name":"Zachary Karas","orcid":"https://orcid.org/0000-0002-5721-8794"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Karas","raw_affiliation_strings":["Department of Computer Science, Vanderbilt University, Nashville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-5721-8794","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058234033","display_name":"Thuy Dung Nguyen","orcid":"https://orcid.org/0000-0002-3489-4255"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thuy Dung Nguyen","raw_affiliation_strings":["Department of Computer Science, Vanderbilt University, Nashville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-3489-4255","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030030910","display_name":"Kevin Leach","orcid":"https://orcid.org/0000-0002-4001-3442"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Leach","raw_affiliation_strings":["Department of Computer Science, Vanderbilt University, Nashville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-4001-3442","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055069752","display_name":"Yu Huang","orcid":"https://orcid.org/0000-0003-2730-5077"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Huang","raw_affiliation_strings":["Department of Computer Science, Vanderbilt University, Nashville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0003-2730-5077","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"616","last_page":"620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.996999979019165,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9939000010490417,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/programmer","display_name":"Programmer","score":0.8202828168869019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7634422779083252},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6207138895988464},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5839676856994629},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5254765748977661},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4301323890686035},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32109254598617554}],"concepts":[{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.8202828168869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634422779083252},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6207138895988464},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5839676856994629},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5254765748977661},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4301323890686035},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32109254598617554},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1145/3696630.3728510","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728510","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696630.3728510","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.14936","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14936","pdf_url":"https://arxiv.org/pdf/2503.14936","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3696630.3728510","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728510","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696630.3728510","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3215465115","display_name":null,"funder_award_id":"CCF-2211429","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412703863.pdf","grobid_xml":"https://content.openalex.org/works/W4412703863.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2604348044","https://openalex.org/W2606555609","https://openalex.org/W2754629507","https://openalex.org/W2911282308","https://openalex.org/W2918028508","https://openalex.org/W2963935794","https://openalex.org/W3038922893","https://openalex.org/W3040102868","https://openalex.org/W4220864612","https://openalex.org/W4390742640","https://openalex.org/W4399632113","https://openalex.org/W4401887005","https://openalex.org/W4407685639"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2972896947","https://openalex.org/W2170146914","https://openalex.org/W2355105570","https://openalex.org/W2083974823","https://openalex.org/W2072751097","https://openalex.org/W622882839","https://openalex.org/W2185017216","https://openalex.org/W2016345697"],"abstract_inverted_index":{"Human":[0],"attention":[1,68,81,118],"provides":[2],"valuable":[3],"yet":[4],"underexploited":[5],"signals":[6,37],"for":[7,38,88,109],"code":[8,39,110,121],"LLM":[9],"training,":[10],"offering":[11],"a":[12,48,71,85,94],"perspective":[13],"beyond":[14],"purely":[15],"machine-driven":[16],"attention.":[17],"Despite":[18],"the":[19,106],"complexity":[20],"and":[21,53,83,116],"cost":[22],"of":[23,130],"collecting":[24],"eye-tracking":[25,61],"data,":[26],"there":[27],"has":[28],"also":[29],"been":[30],"limited":[31],"progress":[32],"in":[33,103,133],"systematically":[34],"using":[35],"these":[36,90],"llm":[40],"training.":[41],"To":[42],"address":[43],"both":[44],"issues,":[45],"we":[46,57],"propose":[47],"cohesive":[49],"pipeline":[50],"spanning":[51],"augmentation":[52,63],"reward-based":[54],"fine-tuning.":[55],"Specifically,":[56],"introduce":[58],"(1)":[59],"an":[60],"path":[62],"method":[64],"to":[65],"expand":[66],"programmer":[67],"datasets,":[69],"(2)":[70],"pattern":[72],"abstraction":[73],"step":[74],"that":[75],"refines":[76],"raw":[77],"fixations":[78],"into":[79,93],"learnable":[80],"motifs,":[82],"(3)":[84],"reward-guided":[86],"strategy":[87],"integrating":[89],"insights":[91],"directly":[92],"CodeT5":[95],"supervised":[96],"fine-tuning":[97],"process.":[98],"Our":[99],"experiments":[100],"yield":[101],"+7.16":[102],"CodeBLEU":[104],"on":[105],"CodeXGlue":[107],"benchmark":[108],"summarization,":[111],"underscoring":[112],"how":[113],"uniting":[114],"human":[115],"machine":[117],"can":[119],"boost":[120],"intelligence.":[122],"We":[123],"hope":[124],"this":[125],"work":[126],"encourages":[127],"broader":[128],"exploration":[129],"human-centric":[131],"methods":[132],"next-generation":[134],"AI4SE.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}