{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006595809,0.0001367824,0.0002077213,0.0001116395,0.0001272969,0.002543654,0.002641667,0.00004425889,0.0002317919],"category_scores_gemma":[0.00001608577,0.0001042445,0.00009261104,0.0005921763,0.00001768638,0.002693441,0.001491619,0.00005817208,0.000118114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004257837,"about_ca_system_score_gemma":0.0001784414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006407076,"about_ca_topic_score_gemma":0.0003276638,"domain_scores_codex":[0.9985551,0.00002500528,0.0002174686,0.000606996,0.0002186425,0.0003768252],"domain_scores_gemma":[0.9989363,0.00004700657,0.00002528353,0.0008176273,0.0000798234,0.00009399294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001188021,0.00002323696,0.00000474389,0.00002061244,0.00004537804,0.000007242006,0.00007371097,0.0009794239,0.00009821718,0.7572579,0.2340512,0.007437109],"study_design_scores_gemma":[0.0001196097,0.00001481419,0.000002749902,0.000009867171,0.00001507032,0.000002846943,0.000009252196,0.6928912,0.0007650931,0.03678529,0.2692599,0.0001242723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006576884,0.0005620282,0.9644563,0.002725398,0.0003219704,0.0002807587,0.0001480013,0.0002357957,0.031204],"genre_scores_gemma":[0.1469489,0.00008996813,0.7529297,0.00307695,0.0002766148,0.0002535664,0.0002741156,0.00004191893,0.09610824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7204726,"threshold_uncertainty_score":0.9984918,"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."}}