{"id":"https://openalex.org/W7166797240","doi":"https://doi.org/10.18653/v1/2026.findings-acl.607","title":"Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction","display_name":"Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166797240","doi":"https://doi.org/10.18653/v1/2026.findings-acl.607"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.607","pdf_url":"https://aclanthology.org/2026.findings-acl.607.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.607.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139806598","display_name":"Su Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Su Lan","raw_affiliation_strings":["Griffith University , Brisbane , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Griffith University , Brisbane , Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030630341","display_name":"Xuefei Yin","orcid":"https://orcid.org/0000-0002-5784-7419"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuefei Yin","raw_affiliation_strings":["Griffith University , Brisbane , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Griffith University , Brisbane , Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139759527","display_name":"Yanming Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yanming Zhu","raw_affiliation_strings":["Griffith University , Brisbane , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Griffith University , Brisbane , Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139827761","display_name":"Alan Wee-Chung Liew","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan Wee-Chung Liew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.78662624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12484","last_page":"12500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.5885999798774719,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.5885999798774719,"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":0.24009999632835388,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.041999999433755875,"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/action","display_name":"Action (physics)","score":0.3059000074863434},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2840000092983246},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.2745000123977661},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2669999897480011},{"id":"https://openalex.org/keywords/causal-chain","display_name":"Causal chain","score":0.2660999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5884000062942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813000023365021},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C79897977","wikidata":"https://www.wikidata.org/wiki/Q5054568","display_name":"Causal chain","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.607","pdf_url":"https://aclanthology.org/2026.findings-acl.607.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.607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.607","pdf_url":"https://aclanthology.org/2026.findings-acl.607.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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166797240.pdf","grobid_xml":"https://content.openalex.org/works/W7166797240.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Causal":[0],"and":[1,18,40,56,115,135,149,167],"intervention-based":[2,63],"question":[3,64],"answering":[4],"is":[5,89],"fundamental":[6],"to":[7],"advancing":[8],"large":[9],"language":[10],"models":[11],"(LLMs)":[12],"toward":[13],"reasoning":[14,38,59,72,116,169],"beyond":[15,141],"surface-level":[16],"correlations":[17],"understanding":[19],"underlying":[20],"causal":[21,35,58,68,76,92,113,122,129],"mechanisms.However,":[22],"existing":[23,161],"LLM-based":[24,162],"methods":[25,163],"often":[26],"rely":[27],"on":[28,145],"implicit":[29,84],"language-level":[30],"reasoning,":[31],"resulting":[32],"in":[33,47],"opaque":[34],"assumptions,":[36],"unverifiable":[37],"paths,":[39],"fragile":[41],"predictions":[42],"under":[43],"complex":[44],"interventions,":[45],"particularly":[46],"contextfree":[48],"settings.In":[49],"this":[50],"paper,":[51],"we":[52],"propose":[53],"an":[54,74],"explicit":[55,75],"auditable":[57,168],"framework":[60,158],"for":[61],"context-free":[62],"answering.Our":[65],"method":[66],"formulates":[67],"inference":[69],"as":[70,101],"structured":[71],"over":[73],"graph":[77,93,106],"through":[78],"four":[79],"modular":[80],"stages,":[81],"rather":[82],"than":[83],"end-to-end":[85],"prediction.A":[86],"key":[87],"innovation":[88],"a":[90,102,120],"target-aware":[91],"construction":[94],"strategy":[95],"that":[96,126,156],"treats":[97],"the":[98],"target":[99],"variable":[100],"core":[103],"constraint":[104],"during":[105],"expansion,":[107],"effectively":[108],"suppressing":[109],"irrelevant":[110],"variables,":[111],"spurious":[112],"relations,":[114],"noise.We":[117],"further":[118],"introduce":[119],"path-level":[121],"evidence":[123],"aggregation":[124],"mechanism":[125],"combines":[127],"multiple":[128],"paths":[130],"while":[131,164],"modeling":[132],"both":[133],"reinforcing":[134],"counteracting":[136],"effects,":[137],"enabling":[138],"robust":[139],"decision-making":[140],"singlechain":[142],"reasoning.Extensive":[143],"experiments":[144],"two":[146],"causal-direction":[147],"benchmarks":[148],"one":[150],"medically":[151],"grounded":[152],"proxy":[153],"benchmark":[154],"demonstrate":[155],"our":[157],"consistently":[159],"outperforms":[160],"providing":[165],"interpretable":[166],"traces.":[170]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}