{"id":"W4414360800","doi":"10.24963/ijcai.2024/1186","title":"Large Language Models for Causal Discovery: Current Landscape and Future Directions","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Transformative learning; Causality (physics); Leverage (statistics); Key (lock); Natural language; Metadata; Causal model","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":[0.06840993,0.001740061,0.003940598,0.006542115,0.001724286,0.01152709,0.006266116,0.00554372,0.01191568],"category_scores_gemma":[0.1624637,0.002085971,0.003048151,0.007583052,0.009069862,0.02950266,0.007060823,0.01199044,0.003130744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006141488,"about_ca_system_score_gemma":0.01040093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0113289,"about_ca_topic_score_gemma":0.009783834,"domain_scores_codex":[0.9732213,0.02077449,0.0008628842,0.002205238,0.0025317,0.0004042699],"domain_scores_gemma":[0.5282876,0.4484525,0.003278748,0.01008422,0.008085868,0.00181103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002474617,0.0002242118,0.005490927,0.00454729,0.0004294765,0.0001341884,0.000998297,0.02210322,0.0002018738,0.5356007,0.02129685,0.4087255],"study_design_scores_gemma":[0.00005424353,0.00006142272,0.0006610388,0.002212031,0.0001001068,0.00009869877,0.0006454408,0.06233485,0.0001429891,0.8786862,0.05492513,0.00007800407],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.005316957,0.3763773,0.4449205,0.1584575,0.00079089,0.000221418,0.001129069,0.001782679,0.01100367],"genre_scores_gemma":[0.1294744,0.3806425,0.4620562,0.01458243,0.006735372,0.001320039,0.001993512,0.0006414252,0.002554067],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.06840993,"threshold_uncertainty_score":0.3617907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01357248978437331,"score_gpt":0.2941172482840146,"score_spread":0.2805447584996413,"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."}}