{"id":"W4401042369","doi":"10.18653/v1/2024.findings-naacl.41","title":"Solving Data-centric Tasks using Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Data modeling; Programming language; Human–computer interaction; Natural language processing; Software engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.003263005,0.001991217,0.001860432,0.001081212,0.001442643,0.005204189,0.00347322,0.002248215,0.006052377],"category_scores_gemma":[0.01430199,0.00182346,0.002852491,0.001690511,0.001150403,0.0106224,0.003786207,0.004149728,0.003851245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001636064,"about_ca_system_score_gemma":0.003492282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01019329,"about_ca_topic_score_gemma":0.02964055,"domain_scores_codex":[0.9970896,0.001326432,0.0002596905,0.0007917633,0.0003913893,0.0001411978],"domain_scores_gemma":[0.9843357,0.01220824,0.0003988299,0.002074219,0.0006113746,0.0003716248],"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":[0.001017592,0.001118789,0.002981279,0.001975171,0.0009357661,0.001025854,0.001408282,0.3939875,0.01544719,0.05629123,0.08642095,0.4373904],"study_design_scores_gemma":[0.0001798035,0.00007170568,0.0002234511,0.00004959571,0.0001009075,0.0001071015,0.0003203849,0.8887212,0.005153758,0.09300179,0.01202876,0.00004166106],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02711002,0.001398055,0.9400016,0.002732921,0.0001876844,0.0003797853,0.002370977,0.01951757,0.006301327],"genre_scores_gemma":[0.2142616,0.00109865,0.7661154,0.0006389221,0.0001714735,0.000598692,0.01019982,0.001726041,0.005189459],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01019329,"threshold_uncertainty_score":0.0202679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04067939778573693,"score_gpt":0.3286579711128834,"score_spread":0.2879785733271465,"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."}}