{"id":"W4400526199","doi":"10.1145/3626772.3657951","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Stage (stratigraphy); Information retrieval; Artificial intelligence; Natural language processing; Biology","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":[0.0002617793,0.00008192461,0.00008095326,0.00007081407,0.00006375925,0.0002716078,0.0004294457,0.00004328462,0.00005477992],"category_scores_gemma":[0.00006557367,0.00006894176,0.00006255913,0.0001924024,0.000009375332,0.0002796086,0.0001649264,0.00008612881,0.00008311217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002852852,"about_ca_system_score_gemma":0.00005799693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000013833,"about_ca_topic_score_gemma":0.00001568168,"domain_scores_codex":[0.9991506,0.0000112784,0.0001473844,0.0003518181,0.0001276364,0.0002112809],"domain_scores_gemma":[0.9994435,0.0001138625,0.00001376623,0.0003430094,0.00003427281,0.00005157992],"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":[0.000006564002,0.00002687547,0.0001069513,0.0001541923,0.00002856359,0.00004522482,0.001398828,0.001334204,0.006826509,0.793744,0.004028546,0.1922996],"study_design_scores_gemma":[0.0001412179,0.00001998363,0.00002615796,0.00002194568,0.000001978363,0.000003535478,0.00001765162,0.9596809,0.002414063,0.0007038238,0.03687164,0.00009717422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004259774,0.000224206,0.9899225,0.001194272,0.0007316628,0.0001403964,0.00000200793,0.0004826562,0.003042488],"genre_scores_gemma":[0.3447899,0.000002301577,0.6172369,0.0002175651,0.0001618905,0.000006784426,0.000001263019,0.00001158742,0.03757175],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9583466,"threshold_uncertainty_score":0.2811363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.111294709817791,"score_gpt":0.3375868433020279,"score_spread":0.2262921334842369,"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."}}