{"id":"https://openalex.org/W7162804475","doi":"https://doi.org/10.48550/arxiv.2605.29648","title":"Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering","display_name":"Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162804475","doi":"https://doi.org/10.48550/arxiv.2605.29648"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29648","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.29648","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132834966","display_name":"Shicheng Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Shicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116717710","display_name":"Haochang Hao","orcid":"https://orcid.org/0009-0003-0480-4313"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Haochang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137320658","display_name":"Dehai Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Dehai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137378351","display_name":"Weihao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Weihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137378696","display_name":"Philip S. Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Philip S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137329271","display_name":"Lu Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Lu","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":null,"has_fulltext":false,"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":0.8571000099182129,"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":0.8571000099182129,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.030300000682473183,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13629","display_name":"Text Readability and Simplification","score":0.011699999682605267,"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":0.7063999772071838},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6996999979019165},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5281999707221985},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.5212000012397766},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49000000953674316},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4846999943256378},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4697999954223633},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.426800012588501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411999702453613},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7063999772071838},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6996999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728999972343445},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.5212000012397766},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4564000070095062},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29648","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.29648","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5788887739181519,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Applying":[0],"reinforcement":[1],"learning":[2],"to":[3,52,100,129,170],"improve":[4],"factual":[5],"accuracy":[6],"in":[7,158],"knowledge-intensive":[8],"question":[9],"answering":[10],"faces":[11],"a":[12,30,75,85,104,109,113],"reward":[13,65,79],"design":[14],"dilemma.":[15],"Response-level":[16],"rewards":[17],"provide":[18],"only":[19,108],"coarse":[20],"supervision":[21],"and":[22,57,97,112,131],"cannot":[23],"distinguish":[24],"correct":[25],"from":[26,89],"incorrect":[27],"statements":[28],"within":[29],"reasoning":[31],"trace.":[32],"Sentence-level":[33],"alternatives":[34],"offer":[35],"finer-grained":[36],"feedback,":[37],"but":[38],"typically":[39],"rely":[40],"on":[41],"NLI":[42],"verifiers,":[43],"LLM":[44],"judges,":[45],"or":[46],"knowledge-verification":[47],"pipelines":[48],"that":[49,80],"are":[50,67],"expensive":[51],"deploy":[53],"at":[54],"RL":[55],"scale":[56],"often":[58],"unreliable":[59],"for":[60,141],"rare-entity":[61],"facts,":[62],"where":[63],"accurate":[64],"signals":[66],"especially":[68],"important.":[69],"We":[70],"propose":[71],"CorVer":[72,93,135],"(Corpus":[73],"Verify),":[74],"lightweight,":[76],"plug-in-ready":[77],"process":[78],"replaces":[81],"neural":[82],"verifiers":[83],"with":[84,144],"corpus-grounded":[86],"signal":[87],"derived":[88],"Wikipedia":[90],"co-occurrence":[91],"statistics.":[92],"assigns":[94],"sentence-level":[95],"credit":[96],"maps":[98],"it":[99],"token-level":[101],"advantages":[102],"via":[103],"simple":[105],"alignment,":[106],"requiring":[107],"0.5B":[110],"extractor":[111],"single":[114],"corpus":[115],"lookup":[116],"per":[117],"sentence.":[118],"Across":[119],"30":[120],"(model,":[121],"benchmark)":[122],"cells":[123,162],"spanning":[124],"six":[125],"instruction-tuned":[126],"models":[127],"(3B":[128],"14B)":[130],"five":[132],"QA":[133],"benchmarks,":[134],"improves":[136],"over":[137],"the":[138],"raw":[139],"baseline":[140],"every":[142],"cell,":[143],"an":[145],"average":[146],"TriviaQA":[147],"gain":[148],"of":[149,160],"+4.1":[150],"pp.":[151],"It":[152],"also":[153],"outperforms":[154],"four":[155],"neural-verifier":[156],"baselines":[157],"18":[159],"20":[161],"under":[163],"their":[164],"feasible":[165],"configurations,":[166],"while":[167],"training":[168],"4.8":[169],"8.4x":[171],"faster.":[172]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}