{"id":"W4404781595","doi":"10.18653/v1/2024.findings-emnlp.564","title":"Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Machine translation; Artificial intelligence; Translation (biology); Resource (disambiguation); Natural language processing; Computer network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001504196,0.001070455,0.0007547461,0.00126083,0.000692789,0.001880136,0.0006856371,0.001002524,0.00272576],"category_scores_gemma":[0.007449247,0.0003315336,0.0008168684,0.0008861683,0.0005374631,0.002170742,0.001524324,0.001538151,0.003287563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003802505,"about_ca_system_score_gemma":0.0006237746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001900562,"about_ca_topic_score_gemma":0.002956524,"domain_scores_codex":[0.9989282,0.0005314182,0.00006583423,0.0001878973,0.0001681477,0.0001184007],"domain_scores_gemma":[0.9963645,0.002124415,0.000209987,0.0004856265,0.0006485881,0.0001667977],"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":[0.00220771,0.0004327876,0.010057,0.0005693737,0.0003075794,0.002880326,0.001050716,0.02860669,0.08738469,0.007307153,0.03885931,0.8203366],"study_design_scores_gemma":[0.0001503905,0.0002786878,0.005778363,0.00007241184,0.000121918,0.001326576,0.001087688,0.9103625,0.052786,0.01780286,0.01013889,0.00009372721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3586039,0.002842845,0.6076114,0.003291477,0.0007667587,0.0001961563,0.002021621,0.01282114,0.01184472],"genre_scores_gemma":[0.8624652,0.0005454098,0.127176,0.0003266791,0.000207718,0.0001024818,0.004129527,0.0007151447,0.004331885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00272576,"threshold_uncertainty_score":0.009118557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02065377648243963,"score_gpt":0.2803603852179046,"score_spread":0.2597066087354649,"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."}}