{"id":"https://openalex.org/W7166806993","doi":"https://doi.org/10.18653/v1/2026.acl-long.751","title":"CoAct: Co-Active LLM Preference Learning with Human-AI Synergy","display_name":"CoAct: Co-Active LLM Preference Learning with Human-AI Synergy","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166806993","doi":"https://doi.org/10.18653/v1/2026.acl-long.751"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.751","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.751","pdf_url":"https://aclanthology.org/2026.acl-long.751.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.751.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139718181","display_name":"Ruiyao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiyao Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139813064","display_name":"Mihir Parmar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mihir Parmar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139746833","display_name":"Tiankai Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiankai Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139748114","display_name":"Zhengyu Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengyu Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139796356","display_name":"Yue Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139730413","display_name":"Kaize Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaize Ding","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7967337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16508","last_page":"16525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.07919999957084656,"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":0.07919999957084656,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.07890000194311142,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.06260000169277191,"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/preference","display_name":"Preference","score":0.41110000014305115},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.26660001277923584},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.2630000114440918},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.257999986410141}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4627000093460083},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26919999718666077},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24799999594688416}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.751","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.751","pdf_url":"https://aclanthology.org/2026.acl-long.751.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.751","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.751","pdf_url":"https://aclanthology.org/2026.acl-long.751.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166806993.pdf","grobid_xml":"https://content.openalex.org/works/W7166806993.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"from":[1],"preference-based":[2],"feedback":[3,90],"has":[4],"become":[5],"an":[6],"effective":[7],"approach":[8],"for":[9],"aligning":[10],"LLMs":[11],"across":[12,106],"diverse":[13],"tasks.However,":[14],"highquality":[15],"human-annotated":[16],"preference":[17],"data":[18,81],"remains":[19],"expensive":[20],"and":[21,67,82,121],"scarce.Existing":[22],"methods":[23],"address":[24],"this":[25,55],"challenge":[26],"through":[27,46,70],"either":[28],"selfrewarding,":[29],"which":[30,43],"scales":[31],"by":[32],"using":[33],"purely":[34],"AIgenerated":[35],"labels":[36],"but":[37,49],"risks":[38],"unreliability,":[39],"or":[40],"active":[41,68],"learning,":[42],"ensures":[44],"quality":[45],"oracle":[47,87,89],"annotation":[48],"cannot":[50],"fully":[51],"leverage":[52],"unlabeled":[53],"data.In":[54],"paper,":[56],"we":[57],"present":[58],"COACT,":[59],"a":[60],"novel":[61],"framework":[62],"that":[63,84],"synergistically":[64],"combines":[65],"selfrewarding":[66],"learning":[69],"strategic":[71],"human-AI":[72],"collaboration.COACT":[73],"leverages":[74],"self-consistency":[75],"to":[76,94],"identify":[77],"both":[78],"reliable":[79],"selflabeled":[80],"samples":[83],"are":[85],"requiring":[86],"verification.Additionally,":[88],"guides":[91],"the":[92],"model":[93,108],"generate":[95],"new":[96],"instructions":[97],"within":[98],"its":[99],"solvable":[100],"capability.Evaluated":[101],"on":[102,116,119,123],"three":[103],"reasoning":[104],"benchmarks":[105],"two":[107],"families,":[109],"COACT":[110],"achieves":[111],"average":[112],"improvements":[113],"of":[114],"+13.25%":[115],"GSM8K,":[117],"+8.19%":[118],"MATH,":[120],"+13.16%":[122],"WebInstruct,":[124],"consistently":[125],"outperforming":[126],"all":[127],"baselines.":[128],"1":[129]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}