{"id":"W6966906186","doi":"10.48448/aw67-ah64","title":"RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Key (lock); Language model; Boosting (machine learning); Realism; Character (mathematics)","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002928577,0.0007789705,0.0008198298,0.00375642,0.0001981278,0.0004005977,0.001573644,0.0003965358,0.00222981],"category_scores_gemma":[0.0002739235,0.000743822,0.0001625411,0.003587293,0.0008291036,0.0007082564,0.0006761357,0.001162957,0.008996389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108992,"about_ca_system_score_gemma":0.001154008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00137819,"about_ca_topic_score_gemma":0.008201811,"domain_scores_codex":[0.9934753,0.0001250874,0.0006233302,0.001890666,0.001929597,0.001956066],"domain_scores_gemma":[0.9980889,0.00006786455,0.0003319556,0.001017702,0.0001021175,0.0003914656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002740874,0.001963969,0.001343853,0.002289511,0.0004956765,0.004193228,0.0520253,0.01020167,0.2695166,0.1159556,0.5212913,0.02044926],"study_design_scores_gemma":[0.002340124,0.00007852159,0.00001651711,0.002871248,0.0001399539,0.00009244813,0.009859575,0.8151348,0.0003494589,0.006672622,0.1603216,0.002123119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.001986801,0.02061914,0.005171847,0.00022173,0.001062042,0.001212243,0.0009776884,0.002293462,0.966455],"genre_scores_gemma":[0.2334779,0.0001653807,0.0284658,0.0008305916,0.001113667,0.0001530017,0.0002957571,0.004175657,0.7313222],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8049331,"threshold_uncertainty_score":0.9995013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01529232375483227,"score_gpt":0.3070958560441719,"score_spread":0.2918035322893397,"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."}}