{"id":"W4413423596","doi":"10.1016/b978-0-443-30046-2.00005-3","title":"Extending large language model capabilities beyond reasoning","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Programming language; Natural language processing; Cognitive science; Linguistics; Psychology; Philosophy","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":[0.0009936644,0.0009045428,0.0006088815,0.0009857424,0.0005709608,0.003931581,0.001598999,0.0008618622,0.02802079],"category_scores_gemma":[0.003981549,0.0009200375,0.001721167,0.001163591,0.001545701,0.01338027,0.002953182,0.003680202,0.009306773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008874683,"about_ca_system_score_gemma":0.0007049415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001677077,"about_ca_topic_score_gemma":0.002022008,"domain_scores_codex":[0.9992169,0.0001831951,0.00005763246,0.0001466728,0.0003446625,0.00005081795],"domain_scores_gemma":[0.9973942,0.00172746,0.00004318244,0.0006453843,0.0001494122,0.00004029037],"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":[0.0000389905,0.00006143187,0.0001772735,0.0004058094,0.00003848846,0.0002197353,0.0004539885,0.007973165,0.005721234,0.6408022,0.04023894,0.3038688],"study_design_scores_gemma":[0.00001070174,0.00001269328,0.00007817972,0.0001267407,0.00004146728,0.0002514809,0.00009388808,0.04169741,0.004859185,0.7623845,0.1904223,0.00002151378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003244296,0.001610912,0.8926101,0.001984201,0.0002997625,0.00005330119,0.0005345699,0.0083599,0.09130298],"genre_scores_gemma":[0.1308697,0.006960681,0.7334864,0.00131321,0.0007010953,0.0002278396,0.004077632,0.005084812,0.1172787],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02802079,"threshold_uncertainty_score":0.09373891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008431370697338129,"score_gpt":0.2590292214334385,"score_spread":0.2505978507361004,"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."}}