{"id":"W4221148028","doi":"10.1007/s11633-022-1387-3","title":"EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training","year":2023,"lang":"en","type":"article","venue":"Machine Intelligence Research","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Open domain; Domain (mathematical analysis); Chatbot; Scale (ratio); Quality (philosophy); Key (lock); Open research; Architecture; Artificial intelligence; Code (set theory); Data science; World Wide Web; Question answering; Computer security","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":[0.002478754,0.0007537582,0.0005546832,0.0008701485,0.001108882,0.001137863,0.001281276,0.000770549,0.003087118],"category_scores_gemma":[0.007609704,0.0003101856,0.0004077939,0.0008066284,0.0006403853,0.001451103,0.001405406,0.001360671,0.000949384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000842509,"about_ca_system_score_gemma":0.001168476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01957517,"about_ca_topic_score_gemma":0.02099637,"domain_scores_codex":[0.9988559,0.0006460803,0.00004550746,0.0002268074,0.0001184222,0.0001072434],"domain_scores_gemma":[0.9940134,0.004580474,0.0001312368,0.0005182947,0.0004449007,0.000311571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005839144,0.005844142,0.1116952,0.002784656,0.00086671,0.002661075,0.02314947,0.2029605,0.1262221,0.01434585,0.04838241,0.4552489],"study_design_scores_gemma":[0.0003222981,0.001251532,0.07392035,0.00005421951,0.0001979192,0.000372756,0.005388801,0.8715513,0.0300718,0.004830266,0.0118703,0.0001684361],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9766338,0.0002402836,0.01492557,0.0001927383,0.00007105594,0.0001975718,0.001675467,0.001758164,0.004305343],"genre_scores_gemma":[0.9780618,0.00006271251,0.01427841,0.00005268563,0.00002789853,0.0002112176,0.004617118,0.0001293282,0.002558779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01957517,"threshold_uncertainty_score":0.03892249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1327379437539389,"score_gpt":0.4119476549633612,"score_spread":0.2792097112094223,"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."}}