{"id":"https://openalex.org/W7135178640","doi":"https://doi.org/10.48550/arxiv.2603.11446","title":"LLM-Assisted Causal Structure Disambiguation and Factor Extraction for Legal Judgment Prediction","display_name":"LLM-Assisted Causal Structure Disambiguation and Factor Extraction for Legal Judgment Prediction","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135178640","doi":"https://doi.org/10.48550/arxiv.2603.11446"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11446","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11446","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.2603.11446","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013217360","display_name":"Yuzhi Liang","orcid":"https://orcid.org/0000-0001-6868-1971"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Yuzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129045923","display_name":"Lixiang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Lixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129064776","display_name":"Xinrong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xinrong","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/T13643","display_name":"Artificial Intelligence in Law","score":0.6428999900817871,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.6428999900817871,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T10028","display_name":"Topic Modeling","score":0.053700000047683716,"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/T14013","display_name":"Legal Language and Interpretation","score":0.02160000056028366,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5999000072479248},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4788999855518341},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.47850000858306885},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4593000113964081},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.445499986410141},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.40070000290870667},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.37560001015663147},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.367900013923645},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.34940001368522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680400013923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6516000032424927},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5789999961853027},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.335999995470047},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.27390000224113464},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11446","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11446","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.2603.11446","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11446","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":"No poverty","score":0.456192284822464,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mainstream":[0],"methods":[1,61],"for":[2],"Legal":[3],"Judgment":[4],"Prediction":[5],"(LJP)":[6],"based":[7],"on":[8,15,166,198],"Pre-trained":[9],"Language":[10,105],"Models":[11],"(PLMs)":[12],"heavily":[13],"rely":[14],"the":[16,152,192],"statistical":[17,110,122],"correlation":[18],"between":[19],"case":[20],"facts":[21],"and":[22,34,45,77,124,131,164,206,221],"judgment":[23,180],"results.":[24],"This":[25],"paradigm":[26],"lacks":[27],"explicit":[28],"modeling":[29],"of":[30],"legal":[31,68,71,134],"constituent":[32,135],"elements":[33],"underlying":[35],"causal":[36,52,59,81,99,111,146,168,175,194],"logic,":[37],"making":[38],"models":[39],"prone":[40],"to":[41,85,128,138,170],"learning":[42],"spurious":[43],"correlations":[44],"suffering":[46],"from":[47],"poor":[48],"robustness.":[49],"While":[50],"introducing":[51],"inference":[53,100],"can":[54],"mitigate":[55],"this":[56],"issue,":[57],"existing":[58],"LJP":[60],"face":[62],"two":[63],"critical":[64],"bottlenecks":[65],"in":[66,80,217,224],"real-world":[67],"texts:":[69],"inaccurate":[70],"factor":[72],"extraction":[73,119],"with":[74,109],"severe":[75],"noise,":[76],"significant":[78],"uncertainty":[79],"structure":[82,147],"discovery":[83],"due":[84],"Markov":[86],"equivalence":[87],"under":[88],"sparse":[89],"features.":[90],"To":[91],"address":[92],"these":[93],"challenges,":[94],"we":[95,114,142,160],"propose":[96],"an":[97,144],"enhanced":[98],"framework":[101],"that":[102,209],"integrates":[103],"Large":[104],"Model":[106],"(LLM)":[107],"priors":[108],"discovery.":[112],"First,":[113],"design":[115],"a":[116,155,178],"coarse-to-fine":[117],"hybrid":[118],"mechanism":[120],"combining":[121],"sampling":[123],"LLM":[125,153],"semantic":[126],"reasoning":[127],"accurately":[129],"identify":[130],"purify":[132],"standard":[133],"elements.":[136],"Second,":[137],"resolve":[139],"structural":[140],"uncertainty,":[141],"introduce":[143],"LLM-assisted":[145],"disambiguation":[148],"mechanism.":[149],"By":[150],"utilizing":[151],"as":[154],"constrained":[156],"prior":[157],"knowledge":[158],"base,":[159],"conduct":[161],"probabilistic":[162],"evaluation":[163],"pruning":[165],"ambiguous":[167],"directions":[169],"generate":[171],"legally":[172],"compliant":[173],"candidate":[174],"graphs.":[176,195],"Finally,":[177],"causal-aware":[179],"prediction":[181],"model":[182],"is":[183],"constructed":[184],"by":[185],"explicitly":[186],"constraining":[187],"text":[188],"attention":[189],"intensity":[190],"via":[191],"generated":[193],"Extensive":[196],"experiments":[197],"multiple":[199],"benchmark":[200],"datasets,":[201],"including":[202],"LEVEN":[203],",":[204],"QA,":[205],"CAIL,":[207],"demonstrate":[208],"our":[210],"proposed":[211],"method":[212],"significantly":[213],"outperforms":[214],"state-of-the-art":[215],"baselines":[216],"both":[218],"predictive":[219],"accuracy":[220],"robustness,":[222],"particularly":[223],"distinguishing":[225],"confusing":[226],"charges.":[227]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-14T00:00:00"}