{"id":"W4406074029","doi":"10.48550/arxiv.2407.16470","title":"Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Machine translation; Translation (biology); Natural language processing; Artificial intelligence; Resource (disambiguation); Linguistics; Psychology; Chemistry; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003447015,0.0001809466,0.0001727475,0.000235021,0.0001506405,0.0001438966,0.0003179348,0.0002326588,0.000002668389],"category_scores_gemma":[0.00001638318,0.00020572,0.00008876532,0.0002681682,0.00002924218,0.0003385169,0.000307554,0.000277667,0.000002946621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001495585,"about_ca_system_score_gemma":0.00004532452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003431679,"about_ca_topic_score_gemma":0.0002850948,"domain_scores_codex":[0.9987497,0.00009141598,0.0001510571,0.000755439,0.00006965043,0.0001827123],"domain_scores_gemma":[0.9991753,0.00009585793,0.0001141187,0.000489097,0.00006828424,0.00005738309],"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":[0.00009414552,0.0001436364,0.00005831377,0.001274779,0.0001008128,0.00004329547,0.005273071,0.5929146,0.002714889,0.2869592,0.000009604317,0.1104136],"study_design_scores_gemma":[0.0002719869,0.00002379756,0.000100693,0.00006961664,0.000063724,0.000003259846,0.0001269015,0.9342785,0.0006867455,0.06411773,0.00006279755,0.0001942132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.226041,0.0004676464,0.772524,0.00008224684,0.0001075255,0.0003620674,0.00006507792,0.0002013129,0.0001490771],"genre_scores_gemma":[0.9939429,0.0000318198,0.005676338,0.00002537606,0.00005755579,0.000002307566,0.00007744081,0.00001602997,0.0001702855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7679018,"threshold_uncertainty_score":0.8389017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05613422021312714,"score_gpt":0.2141775388453185,"score_spread":0.1580433186321914,"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."}}