{"id":"W4404280427","doi":"10.23977/acss.2024.080618","title":"Sparse Attention Mechanisms in Large Language Models: Applications, Classification, Performance Analysis, and Optimization","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Natural language processing; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005623793,0.0001080357,0.0001930987,0.0003648569,0.00005283414,0.0002666021,0.0001914087,0.00004995531,7.691939e-7],"category_scores_gemma":[0.000001348152,0.0001008406,0.00002319048,0.000741206,0.00001179567,0.00116744,0.00008752813,0.00008632244,0.000001399796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003173131,"about_ca_system_score_gemma":0.00001402298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002321067,"about_ca_topic_score_gemma":0.00002643897,"domain_scores_codex":[0.9987822,0.00007651864,0.0003530382,0.0004749869,0.0001516271,0.0001616634],"domain_scores_gemma":[0.9995515,0.0000582854,0.00006541261,0.0002550097,0.00003268234,0.00003714455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.65523e-7,0.00001831639,0.001663596,0.0001544126,0.00001419889,0.000003623295,0.0005145849,0.8752113,0.00006178671,0.0676357,0.000001352776,0.05472016],"study_design_scores_gemma":[0.0001216894,0.00001430556,0.0006066186,0.0001159448,0.000009941062,0.000006479676,0.00007454112,0.997233,0.000008905282,0.001581653,0.000114119,0.0001127705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009024886,0.01632795,0.9739883,0.00006181525,0.0001814588,0.0002884828,0.000003176347,0.00007719643,0.00004671384],"genre_scores_gemma":[0.9004302,0.001719136,0.09763144,0.0000288284,0.00005268802,0.0001002735,0.00001346343,0.000005548957,0.00001844182],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8914053,"threshold_uncertainty_score":0.4112162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02042878749782472,"score_gpt":0.267619407550778,"score_spread":0.2471906200529532,"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."}}