{"id":"W3030151190","doi":"","title":"Evaluating Approaches to Personalizing Language Models","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Perplexity; Computer science; Language model; Personalization; Artificial intelligence; Natural language processing; Adaptation (eye); Word (group theory); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001053915,0.0001104687,0.0001252855,0.00005251955,0.0001140785,0.0001888438,0.0002803518,0.00004034115,0.00002576461],"category_scores_gemma":[0.0001482065,0.0001009112,0.00003385254,0.000211264,0.000009500902,0.0002837761,0.000203755,0.00008878252,0.00001512242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002865746,"about_ca_system_score_gemma":0.00002514483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008509235,"about_ca_topic_score_gemma":0.000008988974,"domain_scores_codex":[0.998462,0.0001598153,0.0001673444,0.0004298649,0.0005870679,0.0001939713],"domain_scores_gemma":[0.9994673,0.0000540815,0.00005693877,0.0002417801,0.00003571631,0.0001442592],"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":[0.000008581416,0.000008421223,0.00006473602,0.00003999841,0.00001262521,0.000004365577,0.3355235,0.09157415,0.004440699,0.00247329,0.0000343199,0.5658153],"study_design_scores_gemma":[0.0002463419,0.00005755024,0.0001157759,0.00002193354,0.00001572484,0.000003920999,0.007921465,0.9907225,0.0003144711,0.0003795442,0.00007342746,0.0001273222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7205886,0.002067743,0.2727377,0.002777445,0.00002841483,0.0002593588,0.000001094539,0.0001015319,0.001438122],"genre_scores_gemma":[0.9282846,0.000002865739,0.07033808,0.00106902,0.0002187771,0.00002821547,0.000004397656,0.000009453503,0.00004461297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8991484,"threshold_uncertainty_score":0.4115039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3079769636386057,"score_gpt":0.3464064700721486,"score_spread":0.03842950643354293,"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."}}