{"id":"https://openalex.org/W7167899784","doi":"https://doi.org/10.1145/3805712.3809601","title":"R 3 Check: Reinforcement Learning for Iterative Retrieval and Structured Reasoning in Complex Fact Checking","display_name":"R 3 Check: Reinforcement Learning for Iterative Retrieval and Structured Reasoning in Complex Fact Checking","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167899784","doi":"https://doi.org/10.1145/3805712.3809601"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809601","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809601","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100778408","display_name":"Peng Qi","orcid":"https://orcid.org/0000-0002-6458-8320"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Peng Qi","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6458-8320","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015645383","display_name":"Yuyang Zhao","orcid":"https://orcid.org/0000-0002-4754-0325"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuyang Zhao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4754-0325","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051209739","display_name":"Wynne Hsu","orcid":"https://orcid.org/0000-0002-4142-8893"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wynne Hsu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4142-8893","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019988958","display_name":"Mong Li Lee","orcid":"https://orcid.org/0000-0002-9636-388X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mong Li Lee","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9636-388X","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94946117,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1473","last_page":"1484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.39340001344680786,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.39340001344680786,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19580000638961792,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12139999866485596,"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","display_name":"Reinforcement learning","score":0.6452999711036682},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.5144000053405762},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4803999960422516},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.42489999532699585},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.36039999127388},{"id":"https://openalex.org/keywords/misinformation","display_name":"Misinformation","score":0.350600004196167},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.31630000472068787},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.3102000057697296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922999858856201},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6452999711036682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6335999965667725},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49059998989105225},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C2776990098","wikidata":"https://www.wikidata.org/wiki/Q13579947","display_name":"Misinformation","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2766999900341034},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C101780184","wikidata":"https://www.wikidata.org/wiki/Q840576","display_name":"Dissemination","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809601","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809601","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2890801081","https://openalex.org/W2950031296","https://openalex.org/W2963469388","https://openalex.org/W2963961878","https://openalex.org/W3121596465","https://openalex.org/W3187658747","https://openalex.org/W3196268181","https://openalex.org/W4221148143","https://openalex.org/W4252076394","https://openalex.org/W4366588626","https://openalex.org/W4382202751","https://openalex.org/W4385570355","https://openalex.org/W4387321091","https://openalex.org/W4389518962","https://openalex.org/W4389519118","https://openalex.org/W4392637187","https://openalex.org/W4402671147","https://openalex.org/W4403883066","https://openalex.org/W4404534210","https://openalex.org/W4409362488","https://openalex.org/W4410088531","https://openalex.org/W4412378039","https://openalex.org/W4412945259","https://openalex.org/W7131849224","https://openalex.org/W7133222840"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"fact-checking":[1,37,160,227],"aims":[2],"to":[3,26,40,96,221],"verify":[4],"the":[5,66,105,113,136,215],"veracity":[6,124],"of":[7,69,217],"claims":[8],"based":[9],"on":[10,122],"related":[11],"evidence,":[12,163],"and":[13,28,45,49,72,111,126,141,164,169,195,203],"has":[14],"become":[15],"increasingly":[16],"important":[17],"as":[18,107],"large":[19],"language":[20],"models":[21,39],"(LLMs)":[22],"make":[23],"it":[24],"easier":[25],"generate":[27],"disseminate":[29],"misinformation":[30],"at":[31],"scale.":[32],"In":[33,82],"open":[34],"settings,":[35,206],"effective":[36,180,223],"requires":[38],"iteratively":[41],"retrieve":[42],"relevant":[43],"evidence":[44],"reason":[46],"over":[47],"noisy":[48],"incomplete":[50],"information.":[51],"While":[52],"recent":[53],"LLM-based":[54],"approaches":[55],"have":[56],"shown":[57],"promising":[58],"reasoning":[59,80,132,142,157,170,198,210],"capabilities,":[60],"prompt-based":[61],"methods":[62,75],"remain":[63],"limited":[64],"by":[65],"inherent":[67],"behaviors":[68,225],"base":[70],"LLMs,":[71,199],"supervised":[73],"fine-tuning":[74],"typically":[76],"require":[77],"costly":[78],"annotated":[79],"trajectories.":[81],"this":[83],"paper,":[84],"we":[85,148],"propose":[86],"R3Check,":[87],"a":[88,150,188],"rule-guided":[89],"reinforcement":[90,219],"learning":[91,220],"framework":[92],"that":[93,143,153],"enables":[94],"LLMs":[95],"perform":[97],"iterative":[98],"retrieval\u2013reasoning":[99,224],"for":[100,226],"multi-hop":[101],"fact-checking.":[102],"R3Check":[103,191],"formulates":[104],"retriever":[106],"an":[108],"external":[109],"environment":[110],"optimizes":[112,167],"model":[114],"using":[115,186],"Group":[116],"Relative":[117],"Policy":[118],"Optimization,":[119],"relying":[120],"only":[121,187],"final":[123],"labels":[125],"format-based":[127],"rewards":[128],"rather":[129],"than":[130],"explicit":[131],"annotations.":[133],"To":[134],"mitigate":[135],"mutual":[137],"interference":[138],"between":[139],"retrieval":[140,168,205],"arises":[144],"under":[145,158,200,228],"joint":[146],"training,":[147],"introduce":[149],"two-stage":[151],"curriculum":[152],"first":[154],"trains":[155],"structured":[156],"closed":[159],"with":[161,171],"gold":[162],"then":[165],"jointly":[166],"real-time":[172,204],"retrieval.":[173],"An":[174],"importance-based":[175],"sampling":[176],"strategy":[177],"further":[178],"strengthens":[179],"supervision":[181],"signals":[182],"during":[183],"training.":[184],"Despite":[185],"7B":[189],"backbone,":[190],"outperforms":[192],"existing":[193],"baselines":[194],"even":[196],"powerful":[197],"both":[201],"given-evidence":[202],"while":[207],"producing":[208],"interpretable":[209],"chains.":[211],"This":[212],"work":[213],"demonstrates":[214],"potential":[216],"pure":[218],"induce":[222],"weak":[229],"supervision.":[230]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-11T00:00:00"}