{"id":"W4401864111","doi":"10.23977/jaip.2024.070306","title":"The Training Process and Methods for LLMs Using an Own Knowledge Base","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Digital Rights Management and Security","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Process (computing); Base (topology); Knowledge base; Computer science; Artificial intelligence; Geography; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01089446,0.0008737867,0.0006224001,0.001597786,0.0007935344,0.002314633,0.003322603,0.001160401,0.004248995],"category_scores_gemma":[0.05547409,0.0008827859,0.001118323,0.001009492,0.001651334,0.006835621,0.003954566,0.004355063,0.002109663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001654764,"about_ca_system_score_gemma":0.003388316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006215004,"about_ca_topic_score_gemma":0.007576865,"domain_scores_codex":[0.9937927,0.00320912,0.0004118264,0.001205518,0.001199198,0.0001817168],"domain_scores_gemma":[0.9771374,0.01375103,0.0006440777,0.005824373,0.0023283,0.0003149533],"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":[0.0002217407,0.0004284293,0.005232001,0.0006328605,0.0001708217,0.0001601562,0.002013007,0.1136692,0.008282325,0.08355038,0.007936991,0.7777021],"study_design_scores_gemma":[0.00004841046,0.0001627507,0.001196528,0.0003068451,0.00005586775,0.0001833569,0.0003650996,0.8657426,0.01719189,0.08366112,0.03102694,0.0000585412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004011109,0.00009197474,0.9918568,0.0003195791,0.00002626845,0.0001541107,0.0001039232,0.002191713,0.001244621],"genre_scores_gemma":[0.08788157,0.0001593957,0.908934,0.0002237657,0.00003120848,0.0005204393,0.0005215137,0.0005401212,0.001188006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01089446,"threshold_uncertainty_score":0.05761611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1852679543090059,"score_gpt":0.4814618281898133,"score_spread":0.2961938738808074,"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."}}