{"id":"W4386566488","doi":"10.18653/v1/2023.findings-eacl.83","title":"Large Language Models are few(1)-shot Table Reasoners","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Vector Institute","funders":"","keywords":"Table (database); Context (archaeology); Computer science; Shot (pellet); Code (set theory); Natural language processing; Artificial intelligence; Programming language; Database; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003328297,0.00009123729,0.0001130475,0.00008895435,0.00008429921,0.0001060063,0.0006435668,0.00004788824,0.00007043572],"category_scores_gemma":[0.00002780781,0.00008123578,0.00003861587,0.0005365518,0.000007006868,0.0004636546,0.0003850576,0.00008793872,0.0003705918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002696347,"about_ca_system_score_gemma":0.00003717778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001256389,"about_ca_topic_score_gemma":0.00007347803,"domain_scores_codex":[0.9988418,0.00002327201,0.0001225453,0.0003418915,0.0002408466,0.0004296896],"domain_scores_gemma":[0.9991434,0.00003336144,0.00003373993,0.0006627699,0.00003285423,0.00009390451],"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":[0.000004122475,0.00008417922,0.0009602209,0.00005378345,0.00003637102,0.0003291212,0.008641575,0.05458133,0.002287958,0.7923315,0.1293675,0.01132231],"study_design_scores_gemma":[0.0001542685,0.000005381401,0.00008823826,0.00001094552,0.000001415736,0.000003766603,0.0006573586,0.9915121,0.000470876,0.004306701,0.002664579,0.0001244366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04213082,0.00007598561,0.9105413,0.001518868,0.0002716269,0.00009178394,0.000004887925,0.001120906,0.04424385],"genre_scores_gemma":[0.9442044,0.00001695775,0.03021362,0.0009704883,0.00007979299,0.00001497041,0.000006152474,0.000012883,0.02448072],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9369307,"threshold_uncertainty_score":0.4763331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04316837089407304,"score_gpt":0.275202534745373,"score_spread":0.2320341638512999,"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."}}