{"id":"https://openalex.org/W7166808562","doi":"https://doi.org/10.18653/v1/2026.acl-long.864","title":"WildReward: Learning Reward Models from In-the-Wild Human Interactions","display_name":"WildReward: Learning Reward Models from In-the-Wild Human Interactions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166808562","doi":"https://doi.org/10.18653/v1/2026.acl-long.864"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.864","doi":"https://doi.org/10.18653/v1/2026.acl-long.864","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.864","pdf_url":"https://aclanthology.org/2026.acl-long.864.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.864.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139741252","display_name":"Hao Peng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Peng","raw_affiliation_strings":["Department of Computer Science and Technology ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology ;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139811573","display_name":"Yunjia Qi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunjia Qi","raw_affiliation_strings":["Department of Computer Science and Technology ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology ;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124398554","display_name":"Xiaozhi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405263052","display_name":"Tsinghua Shenzhen International Graduate School","ror":"https://ror.org/01vceef04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaozhi Wang","raw_affiliation_strings":["Shenzhen International Graduate School , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School , Tsinghua University","institution_ids":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139792049","display_name":"Zijun Yao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijun Yao","raw_affiliation_strings":["Department of Computer Science and Technology ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology ;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730946","display_name":"Lei Hou","orcid":"https://orcid.org/0000-0002-8907-3526","observed_orcids":["https://orcid.org/0000-0002-8907-3526"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Hou","raw_affiliation_strings":["Department of Computer Science and Technology ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology ;","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139720785","display_name":"Juanzi Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juanzi Li","raw_affiliation_strings":["Department of Computer Science and Technology ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology ;","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.43573514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18932","last_page":"18948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.296099990606308,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.296099990606308,"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/T10028","display_name":"Topic Modeling","score":0.24289999902248383,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0722000002861023,"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/reward-models","display_name":"reward models","score":0.8880000114440918},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6370000243186951},{"id":"https://openalex.org/keywords/ordinal-regression","display_name":"ordinal regression","score":0.8050000071525574},{"id":"https://openalex.org/keywords/user-heterogeneity","display_name":"user heterogeneity","score":0.8640000224113464}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4629000127315521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41990000009536743},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.24950000643730164},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.24210000038146973},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.23559999465942383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23430000245571136},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2329999953508377},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.22910000383853912}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.864","doi":"https://doi.org/10.18653/v1/2026.acl-long.864","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.864","pdf_url":"https://aclanthology.org/2026.acl-long.864.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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.864","doi":"https://doi.org/10.18653/v1/2026.acl-long.864","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.864","pdf_url":"https://aclanthology.org/2026.acl-long.864.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166808562.pdf","grobid_xml":"https://content.openalex.org/works/W7166808562.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7140277334","https://openalex.org/W4404781765","https://openalex.org/W4412945186","https://openalex.org/W7133237004","https://openalex.org/W7166827766","https://openalex.org/W4415109460","https://openalex.org/W7134031930","https://openalex.org/W4404792842","https://openalex.org/W4404782303","https://openalex.org/W4405418995"],"abstract_inverted_index":{"Reward":[0],"models":[1,11,46],"(RMs)":[2],"are":[3],"crucial":[4],"for":[5,77],"the":[6,22,40],"training":[7,78,133],"of":[8,25,35],"large":[9],"language":[10],"(LLMs),":[12],"yet":[13],"they":[14],"typically":[15],"rely":[16],"on":[17,84],"large-scale":[18],"human-annotated":[19],"preference":[20,88],"pairs.With":[21],"widespread":[23],"deployment":[24],"LLMs,":[26],"in-the-wild":[27,49],"interactions":[28],"have":[29],"emerged":[30],"as":[31,60],"a":[32,66],"rich":[33],"source":[34,63],"implicit":[36],"reward":[37,45,103,125],"signals.This":[38],"raises":[39],"question:":[41],"Can":[42],"we":[43,53,127],"develop":[44],"directly":[47,83,116],"from":[48,117],"interactions?In":[50],"this":[51,55],"work,":[52],"explore":[54],"possibility":[56],"by":[57],"adopting":[58],"WildChat":[59],"an":[61],"interaction":[62],"and":[64,108,134],"proposing":[65],"pipeline":[67],"to":[68,101,130],"extract":[69],"reliable":[70],"human":[71],"feedback,":[72],"yielding":[73],"186k":[74],"high-quality":[75],"instances":[76],"WILDREWARD":[79,93,114,129],"via":[80],"ordinal":[81],"regression":[82],"user":[85,118],"feedback":[86],"without":[87],"pairs.Extensive":[89],"experiments":[90],"demonstrate":[91],"that":[92,113],"achieves":[94],"comparable":[95],"or":[96],"even":[97],"superior":[98],"performance":[99],"compared":[100],"conventional":[102],"models,":[104],"with":[105],"improved":[106],"calibration":[107],"cross-sample":[109],"consistency.We":[110],"also":[111],"observe":[112,135],"benefits":[115],"diversity,":[119],"where":[120],"more":[121],"users":[122],"yield":[123],"stronger":[124],"models.Finally,":[126],"apply":[128],"online":[131],"DPO":[132],"significant":[136],"improvements":[137],"across":[138],"various":[139],"tasks.":[140]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}