{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001016775,0.0001571777,0.0002581274,0.0009476721,0.00008310108,0.00003822256,0.0008411396,0.0003151301,0.00002350823],"category_scores_gemma":[0.0001133833,0.0001739738,0.00003510337,0.0002210143,0.0001182352,0.002002419,0.0005278756,0.0003153204,0.00001548129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001577873,"about_ca_system_score_gemma":0.0001496192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000164539,"about_ca_topic_score_gemma":0.00004037119,"domain_scores_codex":[0.9984397,0.00004901747,0.0007397854,0.0001642885,0.0004671868,0.0001400137],"domain_scores_gemma":[0.9978717,0.00007544564,0.000657012,0.001006938,0.0003675316,0.00002137888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.728279e-7,0.000004937453,0.00000496428,0.00004769878,0.000006306924,1.104282e-7,0.0009625482,0.004998608,0.000002079477,0.715867,0.000003563524,0.2781013],"study_design_scores_gemma":[0.0003131383,0.00000998899,0.000006931987,0.0001453399,0.00001009095,0.00000493819,0.000315806,0.6577443,0.00002630893,0.3399487,0.001369035,0.0001054154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002004087,0.008346681,0.8723078,0.0008051866,0.0002948184,0.0009800984,0.00004822147,0.0006456596,0.1145674],"genre_scores_gemma":[0.8179163,0.008666486,0.1713025,0.0002657693,0.00002065655,0.0001645256,0.0003589509,0.00003549789,0.001269373],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8159122,"threshold_uncertainty_score":0.7094446,"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."}}