{"id":"https://openalex.org/W7204258642","doi":"https://doi.org/10.48550/arxiv.2608.24350","title":"FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision","display_name":"FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204258642","doi":"https://doi.org/10.48550/arxiv.2608.24350"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.24350","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24350","pdf_url":"https://arxiv.org/pdf/2608.24350","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.24350","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148337943","display_name":"Qiming Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Qiming","raw_affiliation_strings":["School of Computer Science and Engineering , Nanjing University of Science and Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Nanjing University of Science and Technology , Nanjing , China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148282687","display_name":"Wenjie Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Wenjie","raw_affiliation_strings":["School of Computer Science and Engineering , Nanjing University of Science and Technology , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Nanjing University of Science and Technology , Nanjing , China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028086891","display_name":"Xiangqing Shen","orcid":"https://orcid.org/0000-0002-9825-7853","observed_orcids":["https://orcid.org/0000-0002-9825-7853"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen, Xiangqing","raw_affiliation_strings":["School of Intelligence Science and Technology , Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5141034984","display_name":"Rui Xia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia, Rui","raw_affiliation_strings":["School of Intelligence Science and Technology , Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5551999807357788,"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":0.5551999807357788,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.16220000386238098,"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":0.13269999623298645,"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/reinforcement-learning-with-verifiable-rewards","display_name":"reinforcement learning with verifiable rewards","score":0.8190000057220459},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.7940000295639038},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8090000152587891},{"id":"https://openalex.org/keywords/fact-checking","display_name":"fact-checking","score":0.5910000205039978},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.6909999847412109},{"id":"https://openalex.org/keywords/factual-reasoning","display_name":"factual reasoning","score":0.6510000228881836},{"id":"https://openalex.org/keywords/factuality","display_name":"factuality","score":0.5490000247955322}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8654999732971191},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6923999786376953},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6898000240325928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6851000189781189},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6328999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5274999737739563},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.415800005197525},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.4016000032424927},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C205208723","wikidata":"https://www.wikidata.org/wiki/Q372765","display_name":"Credit rating","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C155108698","wikidata":"https://www.wikidata.org/wiki/Q1231081","display_name":"Randomized experiment","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C178350159","wikidata":"https://www.wikidata.org/wiki/Q162714","display_name":"Credit risk","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24350","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24350","pdf_url":"https://arxiv.org/pdf/2608.24350","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.24350","doi":"https://doi.org/10.48550/arxiv.2608.24350","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24350","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.24350","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24350","pdf_url":"https://arxiv.org/pdf/2608.24350","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.483264297246933}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204258642.pdf","grobid_xml":"https://content.openalex.org/works/W7204258642.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0,74],"reduce":[1],"the":[2,36,106,124,154],"hallucination":[3],"risk":[4],"caused":[5],"by":[6,104],"outcome-driven":[7],"rewards":[8,148],"in":[9],"large":[10],"language":[11],"models":[12,166],"trained":[13],"through":[14],"reinforcement":[15],"learning":[16],"with":[17,111],"verifiable":[18],"rewards,":[19],"existing":[20],"mitigation":[21],"approaches":[22],"introduce":[23],"process-level":[24],"factual":[25,33,58,91,128,147,169],"supervision.":[26],"However,":[27],"due":[28],"to":[29,140],"coarse-grained":[30],"aggregation":[31],"of":[32,38,108,113,126,156],"signals":[34,159],"and":[35,51,61,70,149,167],"lack":[37],"reliability":[39,72,139,142],"assessment":[40],"for":[41,137],"these":[42,76],"signals,":[43],"they":[44],"create":[45],"a":[46,85,127],"mismatch":[47],"between":[48],"fact":[49,109],"verification":[50,110,138],"policy":[52,86,114,151,161],"updates.":[53,115],"We":[54],"term":[55],"this":[56],"noisy":[57],"credit":[59,67,71,102],"assignment":[60],"decompose":[62],"it":[63],"into":[64,93],"two":[65],"aspects:":[66],"localization":[68,103],"ambiguity":[69],"ambiguity.":[73],"address":[75],"issues,":[77],"we":[78],"propose":[79],"FARCA":[80,99,174],"(Fact-Aligned":[81],"Reliability-Aware":[82],"Credit":[83],"Assignment),":[84],"optimization":[87],"framework":[88],"that":[89,112,173],"transforms":[90],"supervision":[92],"localized,":[94],"reliability-weighted":[95],"token-level":[96],"training":[97],"signals.":[98],"achieves":[100],"fine-grained":[101],"aligning":[105],"granularity":[107],"It":[116],"further":[117],"introduces":[118],"counterfactual":[119],"evidence":[120,132],"attribution,":[121],"which":[122],"uses":[123],"dependence":[125],"judgment":[129],"on":[130,160],"key":[131],"as":[133],"an":[134],"empirical":[135],"proxy":[136],"compute":[141],"weights.":[143],"These":[144],"weights":[145],"modulate":[146],"local":[150],"advantages,":[152],"reducing":[153],"influence":[155],"potentially":[157],"unreliable":[158],"optimization.":[162],"Experiments":[163],"across":[164],"different":[165],"multiple":[168],"reasoning":[170,182],"benchmarks":[171],"show":[172],"significantly":[175],"improves":[176],"model":[177],"factuality":[178],"while":[179],"preserving":[180],"general":[181],"capabilities.":[183]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-08-27T00:00:00"}