{"id":"W4401042314","doi":"10.18653/v1/2024.naacl-long.335","title":"TableLlama: Towards Open Large Generalist Models for Tables","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Analysis with R","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Generalist and specialist species; Computer science; Programming 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":[0.004811309,0.002204619,0.002842696,0.002666905,0.00186459,0.005978984,0.006319854,0.003336729,0.01886741],"category_scores_gemma":[0.02368053,0.002635554,0.004965674,0.004394806,0.001266057,0.01537734,0.005967093,0.005675209,0.01480866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001597237,"about_ca_system_score_gemma":0.0029138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00876628,"about_ca_topic_score_gemma":0.02180117,"domain_scores_codex":[0.9977361,0.0009458332,0.0001628946,0.0006092994,0.00040506,0.0001406975],"domain_scores_gemma":[0.9919491,0.004751078,0.0002120022,0.002203107,0.0006764278,0.0002082696],"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":[0.001443733,0.0002783434,0.003763047,0.001252802,0.00109383,0.0004129604,0.0007007611,0.1145093,0.002491188,0.1631981,0.3478509,0.363005],"study_design_scores_gemma":[0.0001663487,0.00004251576,0.000232328,0.00009371543,0.00009988713,0.00008440251,0.00007305774,0.6370248,0.0009384486,0.3103759,0.05082304,0.00004563581],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0033843,0.00177129,0.9221933,0.001088642,0.0003741171,0.0001421281,0.01146565,0.05697042,0.002610062],"genre_scores_gemma":[0.08148012,0.001501081,0.8652695,0.001230681,0.0004197564,0.0008692423,0.03478044,0.008564374,0.005884758],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01886741,"threshold_uncertainty_score":0.06311774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05470949858411823,"score_gpt":0.320992085302541,"score_spread":0.2662825867184228,"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."}}