{"id":"W7130684127","doi":"10.1109/swc65939.2025.00306","title":"Can LLMs Aid Expert Elicitation for Causal Modeling?","year":2025,"lang":"","type":"article","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Expert elicitation; Bayesian network; Robustness (evolution); Causal model; Bayesian probability; Entropy (arrow of time); Bayesian statistics; Causal inference","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05458385,0.001580959,0.001172131,0.003479328,0.0008776523,0.003941605,0.002308352,0.002051793,0.008594464],"category_scores_gemma":[0.3447438,0.0008770043,0.001269213,0.001792346,0.001627886,0.008397819,0.004725735,0.002994865,0.002625023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001903571,"about_ca_system_score_gemma":0.00373063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00270506,"about_ca_topic_score_gemma":0.006075452,"domain_scores_codex":[0.9474736,0.04520293,0.001747924,0.002679127,0.00252271,0.000373698],"domain_scores_gemma":[0.5889382,0.3729306,0.0102069,0.01752972,0.00936677,0.00102786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001763009,0.0007854063,0.02740596,0.005059026,0.000870571,0.0008414094,0.01511423,0.08193494,0.01358105,0.134565,0.01771837,0.700361],"study_design_scores_gemma":[0.0003623068,0.0003639802,0.005571548,0.002172065,0.0002730199,0.0006285158,0.003329656,0.4972205,0.01077887,0.443243,0.03577518,0.0002812251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03135734,0.001032785,0.9532783,0.004892955,0.0001397883,0.0004363013,0.001333393,0.001820575,0.005708476],"genre_scores_gemma":[0.3752272,0.0006736451,0.6187116,0.001564197,0.0001230242,0.0009612483,0.001677902,0.0001851374,0.0008760578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05458385,"threshold_uncertainty_score":0.2886704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04432170127200308,"score_gpt":0.3183801185490867,"score_spread":0.2740584172770836,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}