{"id":"W4401044086","doi":"10.18653/v1/2024.findings-naacl.274","title":"Fumbling in Babel: An Investigation into ChatGPT’s Language Identification Ability","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Identification (biology); Computer science; Natural language processing; Artificial intelligence; Linguistics; Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006072104,0.001521705,0.001217065,0.002266929,0.001255388,0.00285828,0.002603611,0.001503396,0.006369728],"category_scores_gemma":[0.03131328,0.0008598059,0.001059403,0.002067653,0.001831333,0.005951946,0.004433885,0.002813044,0.003547599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001183854,"about_ca_system_score_gemma":0.001329739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01033415,"about_ca_topic_score_gemma":0.01169817,"domain_scores_codex":[0.9951128,0.002042663,0.0002957278,0.00129976,0.0008077007,0.0004413498],"domain_scores_gemma":[0.9689125,0.0238497,0.0005859167,0.003359651,0.002505332,0.0007867955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005923973,0.001101737,0.09217644,0.00534721,0.001164599,0.003748696,0.01263534,0.1644924,0.03680573,0.02122855,0.1436981,0.5116773],"study_design_scores_gemma":[0.0003361125,0.001628547,0.02240793,0.0004884974,0.000342781,0.001624994,0.005029009,0.8240432,0.05645121,0.01727493,0.07004752,0.0003252378],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7850289,0.002716253,0.07996754,0.001080701,0.0008126419,0.0002647642,0.009264016,0.09890775,0.02195749],"genre_scores_gemma":[0.8696563,0.0005080156,0.07843509,0.0007524223,0.0001170319,0.0002456631,0.0331621,0.00890922,0.008214187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01033415,"threshold_uncertainty_score":0.03211272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02173305564505803,"score_gpt":0.301173562386556,"score_spread":0.279440506741498,"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."}}