{"id":"W4401042217","doi":"10.18653/v1/2024.naacl-industry.33","title":"Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stornoway Diamond (Canada)","funders":"","keywords":"Automatic summarization; Computer science; Artificial intelligence","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":[0.0008074933,0.00012209,0.0001116671,0.0001311203,0.00008600788,0.000286734,0.0007040689,0.00004184492,0.00002220828],"category_scores_gemma":[0.00001804261,0.00007542752,0.00005860475,0.0004633419,0.000008737541,0.0003044506,0.0001415867,0.000137255,0.000007436792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005223403,"about_ca_system_score_gemma":0.00007671162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006900348,"about_ca_topic_score_gemma":0.0104945,"domain_scores_codex":[0.99884,0.00006075404,0.0002291657,0.0003678283,0.000187813,0.0003144639],"domain_scores_gemma":[0.9991837,0.0002813297,0.00002577527,0.0004414587,0.00003620544,0.00003159137],"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":[0.000002007657,0.00002529323,0.0002976804,0.00003547652,0.0000139681,0.00001277765,0.01664351,0.002567995,0.0001004253,0.9711275,0.0011285,0.008044909],"study_design_scores_gemma":[0.000129699,0.000008677028,0.00005879995,0.00004912426,0.00000330547,0.000001288112,0.0004635736,0.9755097,0.000149933,0.01897132,0.004540825,0.0001137593],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006673075,0.0003325917,0.9170313,0.004109406,0.0003028327,0.0003564256,0.00001328881,0.0002273365,0.07095372],"genre_scores_gemma":[0.9606028,0.0000231714,0.03322552,0.001005673,0.0002212668,0.00007603117,0.00001324566,0.00001698332,0.004815309],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9729417,"threshold_uncertainty_score":0.5856177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02476747805012692,"score_gpt":0.2657033425659284,"score_spread":0.2409358645158015,"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."}}