{"id":"W4392669913","doi":"10.18653/v1/2023.findings-ijcnlp.6","title":"Learning to Diversify Neural Text Generation via Degenerative Model","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Language model; Limiting; Artificial intelligence; Diversity (politics); Repetition (rhetorical device); Machine learning; Natural language processing; Engineering; Linguistics","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":[0.0001376226,0.00007958626,0.0000701366,0.0001063158,0.0001924475,0.0001132782,0.0003302046,0.00003135592,0.00001260976],"category_scores_gemma":[0.00002235071,0.00007413384,0.00002878645,0.0003564614,0.00000529767,0.0003436104,0.0003543088,0.00008867481,0.0003515021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003201903,"about_ca_system_score_gemma":0.00002177288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002845659,"about_ca_topic_score_gemma":0.00001808835,"domain_scores_codex":[0.999141,0.00003622198,0.0001084955,0.0003213872,0.0001876064,0.0002052264],"domain_scores_gemma":[0.9996134,0.00001423154,0.00001959597,0.0002201965,0.00005344302,0.00007911061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.637766e-7,0.000002530028,0.00007065194,7.296902e-7,0.000002257864,0.000002706009,0.001719385,0.9470441,0.01590184,0.005287524,0.002052222,0.02791555],"study_design_scores_gemma":[0.00006569133,0.00002759456,0.00006104616,0.000001053289,0.000001045671,0.00000113091,0.0000380963,0.9939758,0.005236748,0.0003258526,0.0001678324,0.00009807086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2163059,0.000002699208,0.7798329,0.002487708,0.0001694163,0.00007071317,1.994153e-7,0.0003231224,0.0008073548],"genre_scores_gemma":[0.8934545,0.000001258351,0.09917767,0.0009626416,0.0001050545,0.000009520872,0.000003300637,0.000005353049,0.006280702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6806552,"threshold_uncertainty_score":0.4517965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06359297354936129,"score_gpt":0.2703843790303541,"score_spread":0.2067914054809928,"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."}}