{"id":"W4399678864","doi":"10.1075/dt.24006.lom","title":"The rise of large language models informed by not so large corpora of training data","year":2024,"lang":"en","type":"article","venue":"Digital Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Standards Association","funders":"","keywords":"Training (meteorology); Computer science; Training set; Natural language processing; Artificial intelligence; Linguistics; Geography; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01587285,0.001738135,0.00264609,0.00345335,0.0009734111,0.004898737,0.00325649,0.003354611,0.006321214],"category_scores_gemma":[0.076271,0.002243687,0.001557219,0.004531465,0.002649866,0.0139492,0.004652853,0.008601792,0.006278944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001854695,"about_ca_system_score_gemma":0.003281434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003067249,"about_ca_topic_score_gemma":0.005226761,"domain_scores_codex":[0.9895102,0.006490293,0.0003573972,0.001748618,0.001713838,0.0001796915],"domain_scores_gemma":[0.9059303,0.07315218,0.001341764,0.01271843,0.006020216,0.0008371675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001230667,0.0004681301,0.005990111,0.003717325,0.001232685,0.0007239542,0.0008577607,0.1157601,0.01934148,0.09276563,0.1291957,0.6287164],"study_design_scores_gemma":[0.0001485792,0.0001773393,0.002007613,0.0005847983,0.0002712431,0.000373745,0.0003254095,0.6472107,0.007867011,0.2456788,0.09524623,0.0001085512],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01588772,0.01359499,0.9249744,0.02336859,0.002055014,0.0001761796,0.005964939,0.007376247,0.006601981],"genre_scores_gemma":[0.1933864,0.0138655,0.7387174,0.007460193,0.003335326,0.0008141999,0.02893439,0.003133438,0.01035301],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01587285,"threshold_uncertainty_score":0.08394468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05178205753511441,"score_gpt":0.3195388255157452,"score_spread":0.2677567679806308,"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."}}