{"id":"https://openalex.org/W7140073722","doi":"https://doi.org/10.18653/v1/2026.eacl-long.56","title":"Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification","display_name":"Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140073722","doi":"https://doi.org/10.18653/v1/2026.eacl-long.56"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.56","pdf_url":"https://aclanthology.org/2026.eacl-long.56.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.56.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Paul He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yinya Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinya Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mrinmaya Sachan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mrinmaya Sachan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhijing Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhijing Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.39129221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1231","last_page":"1250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.4106000065803528,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.4106000065803528,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.10819999873638153,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.08900000154972076,"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":0.7134000062942505},{"id":"https://openalex.org/keywords/symbolic-trajectory-evaluation","display_name":"Symbolic trajectory evaluation","score":0.414900004863739},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.4041000008583069},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3165999948978424},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3021000027656555},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.2827000021934509},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.27970001101493835}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7134000062942505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6582000255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4875999987125397},{"id":"https://openalex.org/C23123167","wikidata":"https://www.wikidata.org/wiki/Q7661193","display_name":"Symbolic trajectory evaluation","level":3,"score":0.414900004863739},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.56","pdf_url":"https://aclanthology.org/2026.eacl-long.56.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:doi:10.3929/ethz-c-000799385","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/799385","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.56","pdf_url":"https://aclanthology.org/2026.eacl-long.56.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140073722.pdf","grobid_xml":"https://content.openalex.org/works/W7140073722.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4,58],"increasingly":[5],"being":[6],"applied":[7],"to":[8,74,78,88,122],"tasks":[9],"that":[10,24,52,81,104],"involve":[11],"causal":[12,41,56,63,79,93,100,112,126],"reasoning.However,":[13],"current":[14],"benchmarks":[15,102],"often":[16],"rely":[17],"on":[18,96,125],"string":[19],"matching":[20],"or":[21],"surface-level":[22],"metrics":[23],"do":[25],"not":[26],"capture":[27],"whether":[28,54],"the":[29,38],"output":[30],"of":[31,40,111],"a":[32,48,61,116],"model":[33],"is":[34],"formally":[35],"valid":[36],"under":[37],"semantics":[39],"reasoning.To":[42],"address":[43],"this,":[44],"we":[45],"propose":[46],"DOVERIFIER,":[47],"simple":[49],"symbolic":[50],"verifier":[51],"checks":[53],"LLM-generated":[55],"expressions":[57],"derivable":[59],"from":[60,67],"given":[62],"graph":[64],"using":[65],"rules":[66],"do-calculus":[68],"and":[69,99,119],"probability":[70],"theory.This":[71],"allows":[72],"us":[73],"recover":[75],"correct":[76],"answers":[77],"queries":[80],"would":[82],"otherwise":[83],"be":[84],"marked":[85],"incorrect":[86],"due":[87],"superficial":[89],"differences":[90],"in":[91],"their":[92],"semantics.Our":[94],"evaluations":[95],"synthetic":[97],"data":[98],"QA":[101],"show":[103],"DOVERIFIER":[105],"more":[106,117],"accurately":[107],"captures":[108],"semantic":[109],"correctness":[110],"reasoning":[113],"traces,":[114],"offering":[115],"rigorous":[118],"informative":[120],"way":[121],"evaluate":[123],"LLMs":[124],"reasoning.":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}