{"id":"W4396722757","doi":"10.1145/3589334.3645481","title":"Metacognitive Retrieval-Augmented Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Universitas Brawijaya","keywords":"Computer science; Metacognition; Natural language processing; Artificial intelligence; Language model; Information retrieval; Cognition; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002985795,0.00009343831,0.0000953725,0.00009944217,0.00004212826,0.0002148789,0.0003713602,0.00003924412,0.0001286024],"category_scores_gemma":[0.00002001983,0.00007461806,0.00006284237,0.0003479598,0.000007575374,0.0006822887,0.0002342544,0.0001191794,0.0002468419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002892975,"about_ca_system_score_gemma":0.0000449258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001972053,"about_ca_topic_score_gemma":0.000005071728,"domain_scores_codex":[0.9989871,0.00003382048,0.0001367347,0.0003721058,0.0002313514,0.0002388536],"domain_scores_gemma":[0.9994857,0.00006437759,0.0000119446,0.0003377768,0.00003931147,0.00006092346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000320956,0.00003387386,0.000003524254,0.00003013063,0.00006847555,0.0001766906,0.003982702,0.000300578,0.001892052,0.9646729,0.001339116,0.02749679],"study_design_scores_gemma":[0.0001143686,0.000012699,0.000003812157,0.00002467402,0.000008200326,0.000008170962,0.0001420165,0.9769177,0.005573572,0.01577829,0.001309579,0.0001068876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005575836,0.001147345,0.9446942,0.0006694678,0.0003569265,0.00009722308,0.000005150046,0.0007194345,0.04673447],"genre_scores_gemma":[0.9534203,0.00001424687,0.03766841,0.000674525,0.00007360984,0.000004286166,0.000003085514,0.000009402117,0.008132148],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9766172,"threshold_uncertainty_score":0.3172736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02582532322801569,"score_gpt":0.2830062823510828,"score_spread":0.2571809591230672,"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."}}