{"id":"https://openalex.org/W4412944669","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1267","title":"When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback","display_name":"When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944669","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1267"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1267","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1267","pdf_url":"https://aclanthology.org/2025.findings-acl.1267.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.findings-acl.1267.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120391869","display_name":"Jane Pan","orcid":"https://orcid.org/0000-0002-3128-9025","observed_orcids":["https://orcid.org/0000-0002-3128-9025"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jane Pan","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204319","display_name":"Ryan Shar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Shar","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010933763","display_name":"Jacob Pfau","orcid":"https://orcid.org/0000-0002-5771-8465","observed_orcids":["https://orcid.org/0000-0002-5771-8465"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Pfau","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029768722","display_name":"Ameet Talwalkar","orcid":"https://orcid.org/0000-0001-6650-1893","observed_orcids":["https://orcid.org/0000-0001-6650-1893"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ameet Talwalkar","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775952","display_name":"He He","orcid":"https://orcid.org/0000-0002-9118-2449","observed_orcids":["https://orcid.org/0000-0002-9118-2449","https://orcid.org/0009-0005-7805-3780"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He He","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088847857","display_name":"Valerie Chen","orcid":"https://orcid.org/0009-0007-2783-0265","observed_orcids":["https://orcid.org/0009-0007-2783-0265"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valerie Chen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6759,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.97604462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"24672","last_page":"24700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9965999722480774,"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":0.9965999722480774,"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/T10533","display_name":"Teaching and Learning Programming","score":0.000699999975040555,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0005000000237487257,"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/interactive-assessment","display_name":"interactive assessment","score":0.7710000276565552},{"id":"https://openalex.org/keywords/user-feedback","display_name":"user feedback","score":0.6119999885559082},{"id":"https://openalex.org/keywords/model-behavior","display_name":"model behavior","score":0.31200000643730164},{"id":"https://openalex.org/keywords/coding-assistants","display_name":"coding assistants","score":0.44699999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980249881744385},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.540622353553772},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34400343894958496},{"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":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1267","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1267","pdf_url":"https://aclanthology.org/2025.findings-acl.1267.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.18413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.18413","pdf_url":"https://arxiv.org/pdf/2502.18413","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.18413","doi":"https://doi.org/10.48550/arxiv.2502.18413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.18413","pdf_url":null,"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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1267","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1267","pdf_url":"https://aclanthology.org/2025.findings-acl.1267.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1338796077","display_name":"CAREER: Enhancing Diversity and Personalization in Human-AI Collaborative Writing","funder_award_id":"2340345","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"},{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944669.pdf","grobid_xml":"https://content.openalex.org/works/W4412944669.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133240538","https://openalex.org/W4416149880","https://openalex.org/W4407576310","https://openalex.org/W7221126145","https://openalex.org/W4393969224","https://openalex.org/W4414742445","https://openalex.org/W4415798077","https://openalex.org/W4417295946","https://openalex.org/W7134975074","https://openalex.org/W4417257651"],"abstract_inverted_index":{"Programming":[0],"is":[1],"a":[2,40,56],"fundamentally":[3],"interactive":[4,27,88,147],"process,":[5],"yet":[6],"coding":[7,46,143],"assistants":[8],"are":[9,108],"often":[10,83],"evaluated":[11],"using":[12],"static":[13,45,86],"benchmarks":[14,47],"that":[15,49,67,97,102],"fail":[16],"to":[17,30,59,95,113,126,140],"measure":[18],"how":[19,32,123],"well":[20],"models":[21,79,91,124,132],"collaborate":[22],"with":[23,55,111],"users.We":[24],"introduce":[25],"an":[26,146],"evaluation":[28],"pipeline":[29],"examine":[31],"LLMs":[33],"incorporate":[34],"different":[35,105],"types":[36,107],"of":[37,77],"feedback":[38,96,106,128],"in":[39],"collaborative":[41],"setting.Specifically,":[42],"we":[43],"perturb":[44],"so":[48],"the":[50,64,74,151],"code":[51],"model":[52,71,118,142],"must":[53],"interact":[54],"simulated":[57],"user":[58],"retrieve":[60],"key":[61],"information":[62],"about":[63],"problem.We":[65],"find":[66],"interaction":[68],"significantly":[69],"affects":[70],"performance,":[72,114],"as":[73,121],"relative":[75],"rankings":[76],"10":[78],"across":[80],"3":[81],"datasets":[82],"vary":[84],"between":[85,153],"and":[87,129,156],"settings,":[89],"despite":[90],"being":[92],"fairly":[93],"robust":[94],"contains":[98],"errors.We":[99],"also":[100],"observe":[101],"even":[103],"when":[104],"equally":[109],"effective":[110],"respect":[112],"they":[115],"can":[116],"impact":[117],"behaviors":[119],"such":[120],"(1)":[122],"respond":[125],"higher-vs.lower-quality":[127],"(2)":[130],"whether":[131],"prioritize":[133],"aesthetic":[134],"vs.":[135],"functional":[136],"edits.Our":[137],"work":[138],"aims":[139],"\"re-evaluate\"":[141],"capabilities":[144],"through":[145],"lens":[148],"toward":[149],"bridging":[150],"gap":[152],"existing":[154],"evaluations":[155],"real-world":[157],"usage.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":6}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}