{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002545615,0.002007346,0.001686789,0.001548845,0.0007544211,0.001708739,0.002482999,0.002049289,0.006245105],"category_scores_gemma":[0.008772771,0.000730768,0.001850694,0.001202506,0.000621061,0.003718206,0.001614327,0.002924132,0.00803838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113065,"about_ca_system_score_gemma":0.002004263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009706987,"about_ca_topic_score_gemma":0.01945696,"domain_scores_codex":[0.9987965,0.0003950308,0.00009379047,0.0004103352,0.0001681842,0.0001361402],"domain_scores_gemma":[0.9978849,0.001132706,0.00009782377,0.000449677,0.0003256696,0.0001091633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001066416,0.0008735633,0.004309591,0.0008984766,0.0005011359,0.0003035826,0.0003313017,0.1983591,0.05657088,0.004182073,0.03941019,0.6931937],"study_design_scores_gemma":[0.0001507732,0.0003139586,0.0008415565,0.00003266997,0.00009915202,0.0001500461,0.00008919338,0.9620535,0.02201369,0.004147721,0.01004546,0.00006228869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1018779,0.006268847,0.759969,0.0009245143,0.0005705101,0.0005846379,0.002161233,0.1210726,0.006570713],"genre_scores_gemma":[0.4733502,0.0008503816,0.5012764,0.001090983,0.0003199161,0.000862492,0.007746084,0.004041143,0.01046236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009706987,"threshold_uncertainty_score":0.02089196,"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."}}