{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004326995,0.001311305,0.001504535,0.001103258,0.000573296,0.001825973,0.001645828,0.00145993,0.002627087],"category_scores_gemma":[0.01522159,0.0005434541,0.0008396019,0.001466956,0.001055562,0.004150183,0.001812294,0.002184582,0.0008282855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00180189,"about_ca_system_score_gemma":0.001587324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0114383,"about_ca_topic_score_gemma":0.01050483,"domain_scores_codex":[0.9986168,0.0006766583,0.00006900618,0.0002289174,0.0002653947,0.0001431832],"domain_scores_gemma":[0.9926416,0.006026173,0.0002929695,0.0004457877,0.0004671363,0.0001262795],"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":[0.0002508008,0.000193287,0.0015353,0.0002850414,0.0001376392,0.00006822737,0.0001979915,0.6553121,0.004603697,0.04646568,0.004072757,0.2868774],"study_design_scores_gemma":[0.00000615524,0.00002910988,0.0001045889,0.000006627033,0.00001085932,0.00001138933,0.00001345903,0.9866284,0.0007942814,0.01208963,0.0002991357,0.000006278269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.02661519,0.001830593,0.9671662,0.001076826,0.00005520925,0.0000751206,0.00010874,0.001214051,0.001858043],"genre_scores_gemma":[0.6601472,0.002663712,0.3305854,0.0004890617,0.0002970319,0.0003402564,0.000579464,0.0003132018,0.0045847],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.0114383,"threshold_uncertainty_score":0.02288365,"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."}}