{"id":"https://openalex.org/W4412888006","doi":"https://doi.org/10.18653/v1/2025.findings-acl.796","title":"daDPO: Distribution-Aware DPO for Distilling Conversational Abilities","display_name":"daDPO: Distribution-Aware DPO for Distilling Conversational Abilities","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888006","doi":"https://doi.org/10.18653/v1/2025.findings-acl.796"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.796","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.796","pdf_url":"https://aclanthology.org/2025.findings-acl.796.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.796.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhengze Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengze Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695340","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0001-6901-3166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yiqun Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiqun Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101580861","display_name":"Simin Guo","orcid":"https://orcid.org/0000-0002-5729-616X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simin Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101338641","display_name":"Dahua Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015557819","display_name":"Xiaoliang Wang","orcid":"https://orcid.org/0000-0002-3688-4851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoliang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065000009","display_name":"Cam-Tu Nguyen","orcid":"https://orcid.org/0009-0006-9484-6876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen Cam-Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032121414","display_name":"Fei Tan","orcid":"https://orcid.org/0000-0001-7057-581X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83329021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"15421","last_page":"15437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9728000164031982,"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/T12031","display_name":"Speech and dialogue systems","score":0.9728000164031982,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.926800012588501,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7158321142196655},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.5126120448112488},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36641925573349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32019469141960144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09121820330619812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158321142196655},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.5126120448112488},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36641925573349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32019469141960144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09121820330619812},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.796","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.796","pdf_url":"https://aclanthology.org/2025.findings-acl.796.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.796","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.796","pdf_url":"https://aclanthology.org/2025.findings-acl.796.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888006.pdf","grobid_xml":"https://content.openalex.org/works/W4412888006.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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/W3204019825"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,49,112],"(LLMs)":[3],"have":[4],"demonstrated":[5],"exceptional":[6],"performance":[7,109,131],"across":[8],"various":[9],"applications,":[10],"but":[11],"their":[12,25],"conversational":[13,45],"abilities":[14,46],"decline":[15],"sharply":[16],"as":[17,38],"model":[18,150],"size":[19],"decreases,":[20],"presenting":[21],"a":[22,39,51,85,124],"barrier":[23],"to":[24,42,128,136,144],"deployment":[26],"in":[27,107,118],"resource-constrained":[28],"environments.Knowledge":[29],"distillation":[30],"with":[31],"Direct":[32],"Preference":[33],"Optimization":[34],"(dDPO)":[35],"has":[36],"emerged":[37],"promising":[40],"approach":[41],"enhancing":[43,114],"the":[44,65,69,74],"of":[47,138],"smaller":[48,115],"using":[50],"larger":[52],"teacher":[53,149],"model.However,":[54],"current":[55],"methods":[56,106],"primarily":[57],"focus":[58],"on":[59],"\"black-box\"":[60],"KD,":[61],"which":[62],"only":[63],"uses":[64],"teacher's":[66],"responses,":[67],"overlooking":[68],"output":[70],"distribution":[71],"offered":[72],"by":[73,80],"teacher.This":[75],"paper":[76],"addresses":[77],"this":[78],"gap":[79],"introducing":[81],"daDPO":[82,103],"(Distribution-Aware":[83],"DPO),":[84],"unified":[86],"method":[87,122],"for":[88,110],"preference":[89,133],"optimization":[90],"and":[91,98,113,141],"distributionbased":[92],"distillation.We":[93],"provide":[94],"rigorous":[95],"theoretical":[96],"analysis":[97],"empirical":[99],"validation,":[100],"showing":[101],"that":[102,137],"outperforms":[104],"existing":[105],"restoring":[108],"pruned":[111,126],"LLM":[116],"models.Notably,":[117],"indomain":[119],"evaluation,":[120],"our":[121],"enables":[123],"20%":[125],"Vicuna1.5-7B":[127],"achieve":[129],"near-teacher":[130],"(-7.3%":[132],"rate":[134],"compared":[135],"dDPO's":[139],"-31%),":[140],"allows":[142],"Qwen2.5-1.5B":[143],"occasionally":[145],"outperform":[146],"its":[147],"7B":[148],"(14.0%win":[151],"rate).":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}