{"id":"W4378876515","doi":"10.1007/978-3-031-34107-6_34","title":"Towards Automatic Evaluation of NLG Tasks Using Conversational Large Language Models","year":2023,"lang":"en","type":"book-chapter","venue":"IFIP advances in information and communication technology","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Natural language generation; Computer science; Artificial intelligence; Natural language processing; Natural language","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":[0.006694554,0.00265569,0.002509688,0.002730897,0.001354504,0.004819399,0.00265944,0.003010979,0.00854979],"category_scores_gemma":[0.02014444,0.001062449,0.001603061,0.001780812,0.0007624057,0.004714434,0.003432679,0.002638406,0.009161598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519897,"about_ca_system_score_gemma":0.002000804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008820158,"about_ca_topic_score_gemma":0.01101489,"domain_scores_codex":[0.9909733,0.005362059,0.000496437,0.001184045,0.001580499,0.0004037169],"domain_scores_gemma":[0.9835986,0.01093137,0.0003703625,0.001579204,0.003033323,0.0004870649],"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":[0.001911859,0.0007291067,0.003683286,0.001471036,0.0004112309,0.0004546193,0.0007014299,0.06185853,0.07025128,0.006986267,0.06256653,0.7889749],"study_design_scores_gemma":[0.00009826523,0.0001235272,0.001058321,0.0000546479,0.00008812681,0.0001355656,0.0002921053,0.9588858,0.02361612,0.007328937,0.00827251,0.00004612892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06487924,0.003429144,0.8326406,0.001162573,0.0006477914,0.000736583,0.007356931,0.0789366,0.01021051],"genre_scores_gemma":[0.3346021,0.0009393148,0.6185978,0.0004737445,0.0002832546,0.0008394339,0.0311183,0.00478033,0.008365724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008820158,"threshold_uncertainty_score":0.03540462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04236327399656033,"score_gpt":0.3204837379407636,"score_spread":0.2781204639442033,"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."}}