{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001212655,0.0000833172,0.00007913868,0.0001821533,0.00005884515,0.0004338578,0.0004082735,0.00006737345,0.00001894937],"category_scores_gemma":[0.00008049942,0.00007828724,0.00002829157,0.0007407744,0.00004298403,0.00188257,0.00006009048,0.0001241299,0.0001004559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001297988,"about_ca_system_score_gemma":0.00008015319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008791258,"about_ca_topic_score_gemma":0.001225559,"domain_scores_codex":[0.9987313,0.0001250965,0.0003053057,0.0005144599,0.0001886151,0.0001351925],"domain_scores_gemma":[0.9991154,0.00008760575,0.00003045018,0.0006542277,0.00004358534,0.00006874477],"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":[0.00000285672,0.0001041773,0.007109879,0.0002181849,0.000004901026,0.000005411254,0.05163775,0.00019708,0.1741133,0.3392843,0.0000839256,0.4272382],"study_design_scores_gemma":[0.0001069823,0.00004024004,0.2065178,0.00005344623,0.000003868122,0.000005295955,0.001022953,0.6350267,0.04437238,0.1122359,0.0003531416,0.0002613442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7931136,0.0001680382,0.2035147,0.002182957,0.0002247969,0.0001676068,6.405259e-7,0.0004481498,0.0001794839],"genre_scores_gemma":[0.9901547,0.000005463809,0.009489093,0.000110449,0.0000435894,0.00003080069,0.00002319431,0.000005484941,0.0001372071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6348296,"threshold_uncertainty_score":0.4183701,"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."}}