{"id":"W4322096525","doi":"10.1007/978-3-031-24337-0_22","title":"Building Personalized Language Models Through Language Model Interpolation","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Perplexity; Language model; Computer science; Artificial intelligence; Natural language processing; Social media; Interpolation (computer graphics); Cache language model; Natural language; Universal Networking Language; Comprehension approach; World Wide Web","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":[0.001176263,0.001232274,0.001214045,0.001368314,0.0007293257,0.001995872,0.001801561,0.001177496,0.009409558],"category_scores_gemma":[0.004298896,0.001596561,0.00293874,0.001588485,0.0004902983,0.003971796,0.001940573,0.003023063,0.009681283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008519341,"about_ca_system_score_gemma":0.001067715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006201977,"about_ca_topic_score_gemma":0.01074385,"domain_scores_codex":[0.9989815,0.0002734562,0.00005249583,0.0003529115,0.0002544535,0.00008507127],"domain_scores_gemma":[0.9984932,0.0008202241,0.00005261728,0.0003985462,0.0001834689,0.00005201856],"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":[0.0003603681,0.0002704971,0.001399156,0.000362267,0.0003522592,0.0003784943,0.0005208606,0.239835,0.01823075,0.03073929,0.02958912,0.6779619],"study_design_scores_gemma":[0.00002181518,0.0000376709,0.0001796285,0.00002130735,0.00008154415,0.0001491484,0.00006334775,0.9499999,0.008445404,0.03015044,0.01082015,0.00002975677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004134963,0.0002148487,0.9847369,0.00009368925,0.00005619525,0.00005458496,0.000551586,0.008385957,0.0017713],"genre_scores_gemma":[0.1411992,0.0008909223,0.8360733,0.0002511814,0.000114603,0.0003154293,0.005764577,0.003030787,0.01235989],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009409558,"threshold_uncertainty_score":0.03147805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0376111306386286,"score_gpt":0.2919027307924812,"score_spread":0.2542916001538526,"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."}}