{"id":"https://openalex.org/W7166866620","doi":"https://doi.org/10.18653/v1/2026.findings-acl.516","title":"NSF-CoT: Neuro-Symbolic Formal Verification of Chain-of-Thought Faithfulness in Contextual Question Answering","display_name":"NSF-CoT: Neuro-Symbolic Formal Verification of Chain-of-Thought Faithfulness in Contextual Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166866620","doi":"https://doi.org/10.18653/v1/2026.findings-acl.516"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.516","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.516","pdf_url":"https://aclanthology.org/2026.findings-acl.516.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.516.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077294073","display_name":"Vishal Pramanik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishal Pramanik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139851767","display_name":"Maisha Maliha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maisha Maliha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139717299","display_name":"Nathaniel D. Bastian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathaniel D. Bastian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139799488","display_name":"Alvaro Velasquez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alvaro Velasquez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139846902","display_name":"Susmit Jha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Susmit Jha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139843715","display_name":"Sumit Kumar Jha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sumit Kumar Jha","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85546335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10645","last_page":"10663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.41179999709129333,"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":0.41179999709129333,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.05530000105500221,"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/T12268","display_name":"Deception detection and forensic psychology","score":0.030899999663233757,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7010999917984009},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.322299987077713},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.31610000133514404},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3084000051021576},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3025999963283539},{"id":"https://openalex.org/keywords/proposition","display_name":"Proposition","score":0.2906999886035919},{"id":"https://openalex.org/keywords/closed-ended-question","display_name":"Closed-ended question","score":0.2815000116825104}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7010999917984009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6060000061988831},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C2777152325","wikidata":"https://www.wikidata.org/wiki/Q108163","display_name":"Proposition","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C193035329","wikidata":"https://www.wikidata.org/wiki/Q17007046","display_name":"Closed-ended question","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.516","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.516","pdf_url":"https://aclanthology.org/2026.findings-acl.516.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.516","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.516","pdf_url":"https://aclanthology.org/2026.findings-acl.516.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41071775555610657,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166866620.pdf","grobid_xml":"https://content.openalex.org/works/W7166866620.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Chain-of-thought":[0],"(CoT)":[1],"prompting":[2],"makes":[3],"language":[4],"models":[5],"write":[6],"step-by-step":[7],"explanations,":[8],"but":[9,184],"these":[10],"steps":[11,41,178],"may":[12],"not":[13,56,181],"match":[14],"what":[15],"the":[16,31,35,40,46,79,100,134,140,142,150,188],"model":[17,101,143],"actually":[18],"used":[19],"to":[20,95,187],"choose":[21],"its":[22],"answer.Existing":[23],"faithfulness":[24,69,158],"checks":[25,67],"often":[26],"only":[27,182],"test":[28],"whether":[29,39],"changing":[30],"written":[32],"chain":[33],"changes":[34],"answer,":[36],"without":[37],"verifying":[38],"are":[42,180],"truly":[43],"supported":[44],"by":[45,71,133,139],"given":[47],"evidence,":[48],"or":[49],"they":[50],"require":[51],"special":[52],"prompts":[53],"that":[54,66,117,179],"do":[55],"generalize":[57],"well.We":[58],"present":[59],"NSF-CoT,":[60],"a":[61,114,157],"neuro-symbolic":[62],"formal":[63],"verification":[64],"method":[65],"CoT":[68],"step":[70,72,86,112],"for":[73],"contextual":[74],"question":[75],"answering.NSF-CoT":[76],"(1)":[77],"converts":[78],"provided":[80],"context":[81,98],"facts":[82,99,141],"and":[83,108,146,153,162,171,174],"each":[84,106,111],"reasoning":[85,177],"into":[87,156],"simple":[88],"logical":[89],"statements,":[90],"(2)":[91],"uses":[92],"counterfactual":[93],"attribution":[94],"estimate":[96],"which":[97],"relied":[102,144],"on":[103],"while":[104],"generating":[105],"step,":[107,128],"(3)":[109],"verifies":[110],"using":[113],"hybrid":[115],"checker":[116],"combines":[118],"an":[119,123],"SMT":[120],"solver":[121],"with":[122],"LLM-based":[124],"entailment":[125],"judge.For":[126],"every":[127],"we":[129],"score":[130],"groundedness":[131],"(supported":[132,138],"full":[135],"context),":[136],"validity":[137],"on),":[145],"utility":[147],"(helps":[148],"reach":[149],"final":[151,190],"answer),":[152],"combine":[154],"them":[155],"score.Across":[159],"OpenBookQA,":[160],"QASC,":[161],"HotpotQA,":[163],"NSF-CoT":[164],"consistently":[165],"outperforms":[166],"causal":[167],"mediation,":[168],"perturbation":[169],"probes,":[170],"behavioral":[172],"monitoring,":[173],"it":[175],"identifies":[176],"unfaithful":[183],"also":[185],"harmful":[186],"model's":[189],"decision.Our":[191],"code":[192],"is":[193],"available":[194],"here.":[195]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}