{"id":"https://openalex.org/W4415275737","doi":"https://doi.org/10.18653/v1/2026.acl-long.103","title":"ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering","display_name":"ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415275737","doi":"https://doi.org/10.18653/v1/2026.acl-long.103"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.103","pdf_url":"https://aclanthology.org/2026.acl-long.103.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.103.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034714310","display_name":"Simon Lupart","orcid":"https://orcid.org/0009-0008-2383-4557"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Simon Lupart","raw_affiliation_strings":["University of Amsterdam Amsterdam , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam Amsterdam , The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063466614","display_name":"Mohammad Aliannejadi","orcid":"https://orcid.org/0000-0002-9447-4172"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mohammad Aliannejadi","raw_affiliation_strings":["University of Amsterdam Amsterdam , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam Amsterdam , The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055639036","display_name":"Evangelos Kanoulas","orcid":"https://orcid.org/0000-0002-8312-0694"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Evangelos Kanoulas","raw_affiliation_strings":["University of Amsterdam Amsterdam , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam Amsterdam , The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01452282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2257","last_page":"2274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9869999885559082,"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":0.9869999885559082,"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/T12128","display_name":"AI in Service Interactions","score":0.9158999919891357,"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/T12031","display_name":"Speech and dialogue systems","score":0.9125999808311462,"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/question-answering","display_name":"Question answering","score":0.6899999976158142},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6746000051498413},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6678000092506409},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3677000105381012},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.326200008392334},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.32499998807907104},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.2888999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804999947547913},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6899999976158142},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6746000051498413},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6678000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590999722480774},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.103","pdf_url":"https://aclanthology.org/2026.acl-long.103.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"},{"id":"pmh:oai:arXiv.org:2510.13312","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.13312","pdf_url":"https://arxiv.org/pdf/2510.13312","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.13312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.13312","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.103","pdf_url":"https://aclanthology.org/2026.acl-long.103.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":[{"id":"https://openalex.org/G5372375302","display_name":"Personality And Conversational INformatiOn Access (PACINO)","funder_award_id":"215742","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415275737.pdf","grobid_xml":"https://content.openalex.org/works/W4415275737.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"ChatR1,":[2],"a":[3,121],"reasoning":[4,56,90,156,173],"framework":[5],"based":[6],"on":[7,98,108],"reinforcement":[8],"learning":[9],"(RL)":[10],"for":[11],"conversational":[12],"question":[13],"answering":[14],"(CQA).Reasoning":[15],"plays":[16],"an":[17,79],"important":[18],"role":[19],"in":[20,75],"CQA,":[21],"where":[22],"user":[23,93],"intent":[24],"evolves":[25],"across":[26,57,168],"dialogue":[27],"turns,":[28,58],"and":[29,39,44,49,55,61,72,89,101,118,135,158,177],"utterances":[30],"are":[31],"often":[32],"underspecified,":[33],"requiring":[34],"contextual":[35],"interpretation,":[36],"query":[37],"reformulation,":[38],"dynamic":[40],"coordination":[41],"between":[42],"retrieval":[43,88],"generation.Unlike":[45],"static":[46,181],"'rewrite,":[47],"retrieve,":[48],"generate'":[50],"pipelines,":[51],"ChatR1":[52],"interleaves":[53],"search":[54,163],"enabling":[59],"exploratory":[60],"adaptive":[62],"behaviors":[63],"learned":[64],"through":[65],"RL.To":[66],"address":[67],"the":[68,146,149,162],"challenge":[69],"of":[70,124,148,161],"sparse":[71],"delayed":[73],"rewards":[74],"RL,":[76],"we":[77],"propose":[78],"intent-aware":[80,150],"reward":[81],"that":[82,171],"provides":[83],"turn-level":[84],"feedback":[85],"by":[86,113],"aligning":[87],"with":[91],"evolving":[92,131],"goals.ChatR1":[94],"demonstrates":[95],"strong":[96],"performance":[97,140],"both":[99],"3B":[100],"7B":[102],"model":[103],"backbones,":[104],"outperforming":[105],"competitive":[106],"models":[107],"five":[109],"CQA":[110,125,182],"datasets,":[111],"measured":[112],"different":[114],"metrics":[115],"(F1,":[116],"BERTScore,":[117],"LLMas-judge).We":[119],"include":[120],"diverse":[122,155],"set":[123],"datasets":[126],"to":[127],"cover":[128],"topic":[129],"shifts,":[130],"intents,":[132],"mixed-initiative":[133],"dialogues,":[134],"multi-document":[136],"grounding,":[137],"testing":[138],"ChatR1's":[139],"from":[141],"various":[142],"aspects.Ablation":[143],"studies":[144],"confirm":[145],"effectiveness":[147],"reward.Our":[151],"analyses":[152],"further":[153],"reveal":[154],"trajectories":[157],"effective":[159],"use":[160],"tool.ChatR1":[164],"also":[165],"generalizes":[166],"robustly":[167],"domains,":[169],"demonstrating":[170],"RL-based":[172],"enables":[174],"more":[175],"flexible":[176],"context-aware":[178],"behavior":[179],"than":[180],"pipelines.":[183],"1":[184]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-17T00:00:00"}