{"id":"W4404783714","doi":"10.18653/v1/2024.emnlp-industry.86","title":"Query-OPT: Optimizing Inference of Large Language Models via Multi-Query Instructions in Meeting Summarization","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stornoway Diamond (Canada)","funders":"","keywords":"Computer science; Automatic summarization; RDF query language; Query language; Inference; Query optimization; Web search query; Query expansion; Sargable; Information retrieval; Web query classification; Query by Example; Artificial intelligence; Search engine","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":[0.003212179,0.001980017,0.001294835,0.0008434067,0.0006865895,0.001701648,0.002600624,0.00148142,0.00665142],"category_scores_gemma":[0.0131886,0.0006928483,0.001251531,0.001089302,0.000621761,0.003609479,0.001904815,0.002267607,0.002978661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001116393,"about_ca_system_score_gemma":0.002530836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01389177,"about_ca_topic_score_gemma":0.02381394,"domain_scores_codex":[0.9974093,0.001157542,0.0001633178,0.0006895022,0.0003680071,0.0002123328],"domain_scores_gemma":[0.9948552,0.0036018,0.0002004054,0.0007105478,0.0004537092,0.0001782399],"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":[0.002885961,0.0007206532,0.008811925,0.00138764,0.0004501131,0.0005030476,0.001882971,0.1893675,0.05767834,0.009903153,0.06494578,0.6614629],"study_design_scores_gemma":[0.0001581847,0.0001896062,0.000885697,0.00001421246,0.00007931356,0.00008032758,0.0003864896,0.9687066,0.01659799,0.006102631,0.006757059,0.00004181983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05486945,0.0008716522,0.7923715,0.0009108652,0.0001783466,0.0003587315,0.003456524,0.1450294,0.001953587],"genre_scores_gemma":[0.3519057,0.000241124,0.6279935,0.0005641897,0.0001387218,0.0003311384,0.01111881,0.0046579,0.003048816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01389177,"threshold_uncertainty_score":0.02762187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0252817177744218,"score_gpt":0.288662784964189,"score_spread":0.2633810671897672,"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."}}