{"id":"https://openalex.org/W7077911579","doi":"https://doi.org/10.48550/arxiv.2508.16983","title":"ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation","display_name":"ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation","publication_year":2025,"publication_date":"2025-08-23","ids":{"openalex":"https://openalex.org/W7077911579","doi":"https://doi.org/10.48550/arxiv.2508.16983"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2508.16983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.16983","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2508.16983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pozzi, Riccardo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pozzi, Riccardo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Palmonari, Matteo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Palmonari, Matteo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Coletta, Andrea","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Coletta, Andrea","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bellomarini, Luigi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bellomarini, Luigi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lehmann, Jens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lehmann, Jens","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Vahdati, Sahar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vahdati, Sahar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.41760000586509705,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.41760000586509705,"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/T13177","display_name":"Geological and Geophysical Studies","score":0.03460000082850456,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13067","display_name":"Geological Modeling and Analysis","score":0.030300000682473183,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7350000143051147},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5206000208854675},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4465000033378601},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.43630000948905945},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.412200003862381},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4011000096797943},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.40059998631477356},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.38690000772476196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919999957084656},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7350000143051147},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5037000179290771},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4465000033378601},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.34599998593330383},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2508.16983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.16983","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2508.16983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.16983","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5873616337776184,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Knowledge":[0,106],"gaps":[1],"and":[2,32,59,114,154,170],"hallucinations":[3],"are":[4,108],"persistent":[5],"challenges":[6],"for":[7,120],"Large":[8],"Language":[9],"Models":[10],"(LLMs),":[11],"which":[12,136],"generate":[13],"unreliable":[14],"responses":[15],"when":[16],"lacking":[17],"the":[18,62,129],"necessary":[19],"information":[20],"to":[21,36,64,82,125,159,167],"fulfill":[22],"user":[23],"instructions.":[24],"Existing":[25],"approaches,":[26],"such":[27],"as":[28],"Retrieval-Augmented":[29],"Generation":[30],"(RAG)":[31],"tool":[33],"use,":[34],"aim":[35],"address":[37],"these":[38],"issues":[39],"by":[40],"incorporating":[41],"external":[42,84,127],"knowledge.":[43],"Yet,":[44],"they":[45],"rely":[46],"on":[47,88,151],"additional":[48],"models":[49],"or":[50,90],"services,":[51],"resulting":[52],"in":[53,110,116],"complex":[54],"pipelines,":[55],"potential":[56],"error":[57],"propagation,":[58],"often":[60],"requiring":[61],"model":[63],"process":[65],"a":[66,76,99,105,117],"large":[67,160],"number":[68],"of":[69,140],"tokens.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"present":[75],"scalable":[77],"method":[78],"that":[79,142,156],"enables":[80],"LLMs":[81],"access":[83],"knowledge":[85,161],"without":[86],"depending":[87],"retrievers":[89],"auxiliary":[91],"models.":[92],"Our":[93],"approach":[94],"uses":[95],"constrained":[96,134],"generation":[97,135],"with":[98,133,177],"pre-built":[100],"prefix-tree":[101],"index.":[102],"Triples":[103],"from":[104],"Graph":[107],"verbalized":[109],"textual":[111],"facts,":[112],"tokenized,":[113],"indexed":[115],"prefix":[118],"tree":[119],"efficient":[121],"access.":[122],"During":[123],"inference,":[124],"acquire":[126],"knowledge,":[128],"LLM":[130],"generates":[131],"facts":[132],"allows":[137],"only":[138],"sequences":[139],"tokens":[141],"form":[143],"an":[144],"existing":[145],"fact.":[146],"We":[147],"evaluate":[148],"our":[149],"proposal":[150],"Question":[152],"Answering":[153],"show":[155],"it":[157],"scales":[158],"bases":[162],"(800":[163],"million":[164],"facts),":[165],"adapts":[166],"domain-specific":[168],"data,":[169],"achieves":[171],"effective":[172],"results.":[173],"These":[174],"gains":[175],"come":[176],"minimal":[178],"generation-time":[179],"overhead.":[180],"ReFactX":[181],"code":[182],"is":[183],"available":[184],"at":[185],"https://github.com/rpo19/ReFactX.":[186]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}