{"id":"W4409363778","doi":"10.1609/aaai.v39i24.34710","title":"Tuning-Free Accountable Intervention for LLM Deployment – a Metacognitive Approach","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Software deployment; Metacognition; Intervention (counseling); Psychology; Psychotherapist; Computer science; Neuroscience; Cognition; Psychiatry","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":[0.005541226,0.001460892,0.0007498354,0.001114419,0.0009182378,0.003593857,0.003724196,0.001808023,0.006335805],"category_scores_gemma":[0.0383561,0.0008145855,0.0009586867,0.0004851817,0.002928951,0.006504168,0.006138267,0.003309019,0.00120284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001437083,"about_ca_system_score_gemma":0.002428635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002913059,"about_ca_topic_score_gemma":0.002925303,"domain_scores_codex":[0.9952759,0.002405982,0.0002587508,0.0009975486,0.0007267402,0.0003351568],"domain_scores_gemma":[0.9837177,0.008580399,0.001324682,0.00472632,0.0009662324,0.0006846797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008058372,0.0008195982,0.01031192,0.0005254583,0.0002564694,0.001047172,0.009552148,0.1569154,0.02481543,0.3481556,0.007626127,0.4391688],"study_design_scores_gemma":[0.00007137704,0.0001263406,0.0008777018,0.00009917207,0.00007571759,0.0001683616,0.000449328,0.7040474,0.01107446,0.2717128,0.01121731,0.00007994215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01219599,0.00004873026,0.9782448,0.0009625119,0.00002713608,0.0001210619,0.00005816484,0.004442406,0.003899138],"genre_scores_gemma":[0.596769,0.00008269432,0.399368,0.0003429103,0.00003796446,0.0003409081,0.0001528482,0.0005494665,0.00235617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006335805,"threshold_uncertainty_score":0.0293051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0874622275211003,"score_gpt":0.3196241001394326,"score_spread":0.2321618726183323,"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."}}