{"id":"https://openalex.org/W7162773939","doi":"https://doi.org/10.48550/arxiv.2605.29712","title":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies","display_name":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162773939","doi":"https://doi.org/10.48550/arxiv.2605.29712"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29712","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.29712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101858176","display_name":"Yuxuan Ye","orcid":"https://orcid.org/0000-0003-3516-5270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137327986","display_name":"Raul Santos-Rodriguez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santos-Rodriguez, Raul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137375620","display_name":"Edwin Simpson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simpson, Edwin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.666100025177002,"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":0.666100025177002,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.11469999700784683,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.03280000016093254,"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/correctness","display_name":"Correctness","score":0.7468000054359436},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6658999919891357},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6549999713897705},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5943999886512756},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.47909998893737793},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.4733999967575073},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.46470001339912415},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4641999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628999948501587},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7468000054359436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6658999919891357},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6549999713897705},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5497999787330627},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5246000289916992},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.4733999967575073},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42750000953674316},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25110000371932983},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29712","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.29712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29712","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8378722071647644}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Grounded":[0],"claim":[1,55],"factuality":[2,56,97,140],"checking":[3,57,124],"is":[4],"important":[5],"for":[6,71],"large":[7],"language":[8,116],"model":[9],"(LLM)":[10],"applications":[11],"such":[12],"as":[13,16,58],"retrieval-augmented":[14],"generation,":[15],"it":[17],"helps":[18],"users":[19],"assess":[20],"the":[21,44,104,123,134,146],"correctness":[22],"of":[23,47,103],"generated":[24],"outputs.":[25],"Existing":[26],"metrics":[27],"using":[28],"entailment":[29],"classifiers":[30],"require":[31],"dataset-specific":[32],"threshold":[33],"tuning,":[34],"while":[35],"LLM-based":[36],"approaches":[37],"often":[38],"use":[39],"direct":[40],"prompting,":[41],"which":[42],"underutilises":[43],"reasoning":[45],"capabilities":[46],"LLMs.":[48],"We":[49],"address":[50],"this":[51],"by":[52,79],"formulating":[53],"grounded":[54],"a":[59,100,131],"true/false":[60],"reading":[61],"comprehension":[62],"task":[63],"and":[64,87,130,167],"prompting":[65],"LLMs":[66,121],"with":[67,152,159],"explicit":[68],"test-taking":[69],"strategies":[70],"efficient":[72],"reasoning.":[73],"Our":[74],"method":[75],"reduces":[76],"token":[77],"usage":[78],"over":[80],"80%":[81],"compared":[82],"to":[83,91,119,137,163],"unguided":[84],"open-ended":[85],"reasoning,":[86],"achieves":[88],"competitive":[89],"performance":[90],"more":[92],"expensive":[93],"alternatives":[94],"across":[95],"two":[96],"benchmarks,":[98],"setting":[99],"new":[101],"state":[102],"art":[105],"on":[106,150],"one.":[107],"To":[108],"further":[109],"reduce":[110],"inference":[111,157],"cost,":[112],"we":[113],"train":[114],"small":[115],"models":[117],"(SLMs)":[118],"replace":[120],"in":[122],"pipeline.":[125],"Using":[126],"supervised":[127],"fine-tuning":[128],"(SFT)":[129],"self-revision":[132],"mechanism,":[133],"SLMs":[135,148],"learn":[136],"improve":[138],"their":[139],"judgements.":[141],"Experimental":[142],"results":[143],"show":[144],"that":[145],"resulting":[147],"perform":[149],"par":[151],"strong":[153],"baselines,":[154],"combining":[155],"low":[156],"costs":[158],"generating":[160],"supporting":[161],"rationales":[162],"support":[164],"interpretability.":[165],"Code":[166],"datasets":[168],"will":[169],"be":[170],"released":[171],"upon":[172],"acceptance.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-30T00:00:00"}