{"id":"W4389520276","doi":"10.18653/v1/2023.findings-emnlp.703","title":"Investigating the Effect of Pre-finetuning BERT Models on NLI Involving Presuppositions","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Institut de Valorisation des Données; Canadian Institute for Advanced Research","keywords":"Computer science; Leverage (statistics); Presupposition; Artificial intelligence; Exploit; Machine learning; Task (project management); Theoretical computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005622763,0.002817385,0.001374996,0.0008157491,0.0006928685,0.002371533,0.002412969,0.00254349,0.003434046],"category_scores_gemma":[0.03643,0.0007538376,0.001016887,0.0005800035,0.001099182,0.004943105,0.002733382,0.006557632,0.001881941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001100379,"about_ca_system_score_gemma":0.001315766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006225663,"about_ca_topic_score_gemma":0.008959459,"domain_scores_codex":[0.9981728,0.0007944996,0.000123839,0.000595796,0.0001111844,0.0002019859],"domain_scores_gemma":[0.9762287,0.01847224,0.0008314322,0.002982202,0.0008631363,0.0006223845],"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":[0.002808344,0.002835867,0.03956182,0.00137632,0.0008299311,0.0006329002,0.001865118,0.4742883,0.04392332,0.003348144,0.007674484,0.4208554],"study_design_scores_gemma":[0.0001553161,0.001024202,0.004458441,0.0001305032,0.0001880132,0.0001762097,0.0005873438,0.9534301,0.0293101,0.007796358,0.002659635,0.00008369078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8588023,0.002895627,0.1180536,0.00188361,0.0005066679,0.0004220588,0.0007713972,0.007617866,0.009046862],"genre_scores_gemma":[0.9541312,0.0002931194,0.04139753,0.0004962537,0.00006645946,0.0001830364,0.001418793,0.0004258871,0.001587681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006225663,"threshold_uncertainty_score":0.02973634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03633354126024544,"score_gpt":0.2722307729428622,"score_spread":0.2358972316826168,"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."}}