{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04093151,0.002124774,0.001675756,0.004737976,0.001321046,0.004565788,0.002397554,0.003610964,0.002005492],"category_scores_gemma":[0.127417,0.0009409156,0.00164721,0.0028031,0.001466242,0.008082716,0.003337561,0.003214137,0.0006081397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003403644,"about_ca_system_score_gemma":0.002988666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00896824,"about_ca_topic_score_gemma":0.01218979,"domain_scores_codex":[0.9626303,0.02760296,0.001848835,0.00280948,0.004513926,0.0005944825],"domain_scores_gemma":[0.7904698,0.1910407,0.002701092,0.008089342,0.005878296,0.001820724],"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":[0.006334724,0.003655672,0.03196119,0.001922498,0.002634977,0.0001614866,0.002927196,0.2321475,0.005953657,0.01322066,0.007822404,0.691258],"study_design_scores_gemma":[0.0006525703,0.001410466,0.004714962,0.0001928941,0.001468409,0.0001196378,0.0008012542,0.9546984,0.007566678,0.02566815,0.002595341,0.0001110755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4724972,0.01110287,0.4950416,0.002418332,0.0003952516,0.001810054,0.001202132,0.005039508,0.01049305],"genre_scores_gemma":[0.8015619,0.001617974,0.1918664,0.0003511941,0.000171298,0.0006186442,0.001671994,0.0003203298,0.001820252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04093151,"threshold_uncertainty_score":0.2164691,"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."}}