{"id":"W4388787825","doi":"10.48550/arxiv.2311.09696","title":"Fumbling in Babel: An Investigation into ChatGPT's Language Identification Ability","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"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":"Computer science; Variety (cybernetics); Benchmark (surveying); Set (abstract data type); Identification (biology); Resource (disambiguation); Natural language processing; Language identification; Gamut; Artificial intelligence; Range (aeronautics); Compiler; Linguistics; Programming language; Natural language","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":[0.006729288,0.001423777,0.001176893,0.002198186,0.001301301,0.002727551,0.002514245,0.001507546,0.005128218],"category_scores_gemma":[0.02871035,0.0008050808,0.001002335,0.002031768,0.001919785,0.005345218,0.004526863,0.002783985,0.002855152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00116502,"about_ca_system_score_gemma":0.001285152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009775208,"about_ca_topic_score_gemma":0.01098403,"domain_scores_codex":[0.9947112,0.002294084,0.0002791178,0.001345213,0.0008833148,0.0004871758],"domain_scores_gemma":[0.9706461,0.02264142,0.0005411438,0.003219607,0.002227567,0.0007241332],"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":[0.005818065,0.00112377,0.09627151,0.004464683,0.001145255,0.003600256,0.01085335,0.1850586,0.03572636,0.02772568,0.1267941,0.5014183],"study_design_scores_gemma":[0.0002542039,0.001248702,0.01724629,0.0003420534,0.000264397,0.001345661,0.003611583,0.8586271,0.04704767,0.01960445,0.05015463,0.0002532899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7951217,0.002659669,0.09403986,0.001160961,0.0007531389,0.0002393063,0.007733861,0.0782686,0.02002289],"genre_scores_gemma":[0.8773351,0.0004845411,0.08209149,0.0007449098,0.0001206307,0.0002371605,0.02560729,0.006258999,0.00711992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009775208,"threshold_uncertainty_score":0.03558832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07339839838717734,"score_gpt":0.241882152358714,"score_spread":0.1684837539715367,"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."}}