Index of /helm/benchmark_output/releases/mmlu/groups/latex

[ICO]NameLast modifiedSizeDescription

[DIR]Parent Directory  -  
[   ]mmlu_world_religions_mmlu_world_religions_subject:world_religions.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_virology_mmlu_virology_subject:virology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_sociology_mmlu_sociology_subject:sociology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_security_studies_mmlu_security_studies_subject:security_studies.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_public_relations_mmlu_public_relations_subject:public_relations.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_professional_psychology_mmlu_professional_psychology_subject:professional_psychology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_professional_law_mmlu_professional_law_subject:professional_law.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_professional_accounting_mmlu_professional_accounting_subject:professional_accounting.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_prehistory_mmlu_prehistory_subject:prehistory.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_nutrition_mmlu_nutrition_subject:nutrition.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_moral_scenarios_mmlu_moral_scenarios_subject:moral_scenarios.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_moral_disputes_mmlu_moral_disputes_subject:moral_disputes.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_miscellaneous_mmlu_miscellaneous_subject:miscellaneous.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_medical_genetics_mmlu_medical_genetics_subject:medical_genetics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_marketing_mmlu_marketing_subject:marketing.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_management_mmlu_management_subject:management.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_machine_learning_mmlu_machine_learning_subject:machine_learning.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_logical_fallacies_mmlu_logical_fallacies_subject:logical_fallacies.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_international_law_mmlu_international_law_subject:international_law.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_human_sexuality_mmlu_human_sexuality_subject:human_sexuality.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_human_aging_mmlu_human_aging_subject:human_aging.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_world_history_mmlu_high_school_world_history_subject:high_school_world_history.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_us_history_mmlu_high_school_us_history_subject:high_school_us_history.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_statistics_mmlu_high_school_statistics_subject:high_school_statistics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_psychology_mmlu_high_school_psychology_subject:high_school_psychology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_physics_mmlu_high_school_physics_subject:high_school_physics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_microeconomics_mmlu_high_school_microeconomics_subject:high_school_microeconomics.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_high_school_mathematics_mmlu_high_school_mathematics_subject:high_school_mathematics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_macroeconomics_mmlu_high_school_macroeconomics_subject:high_school_macroeconomics.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_high_school_government_and_politics_mmlu_high_school_government_and_politics_subject:high_school_government_and_politics.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_high_school_geography_mmlu_high_school_geography_subject:high_school_geography.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_european_history_mmlu_high_school_european_history_subject:high_school_european_history.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_high_school_computer_science_mmlu_high_school_computer_science_subject:high_school_computer_science.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_chemistry_mmlu_high_school_chemistry_subject:high_school_chemistry.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_high_school_biology_mmlu_high_school_biology_subject:high_school_biology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_formal_logic_mmlu_formal_logic_subject:formal_logic.tex27-Mar-2024 21:39 1.0K 
[   ]mmlu_elementary_mathematics_mmlu_elementary_mathematics_subject:elementary_mathematics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_electrical_engineering_mmlu_electrical_engineering_subject:electrical_engineering.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_conceptual_physics_mmlu_conceptual_physics_subject:conceptual_physics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_college_physics_mmlu_college_physics_subject:college_physics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_college_medicine_mmlu_college_medicine_subject:college_medicine.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_college_mathematics_mmlu_college_mathematics_subject:college_mathematics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_college_computer_science_mmlu_college_computer_science_subject:college_computer_science.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_college_biology_mmlu_college_biology_subject:college_biology.tex27-Mar-2024 21:39 1.0K 
[   ]mmlu_clinical_knowledge_mmlu_clinical_knowledge_subject:clinical_knowledge.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_business_ethics_mmlu_business_ethics_subject:business_ethics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_astronomy_mmlu_astronomy_subject:astronomy.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_us_foreign_policy_mmlu_us_foreign_policy_subject:us_foreign_policy.tex27-Mar-2024 21:39 2.0K 
[   ]mmlu_professional_medicine_mmlu_professional_medicine_subject:professional_medicine.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_philosophy_mmlu_philosophy_subject:philosophy.tex27-Mar-2024 21:39 1.0K 
[   ]mmlu_jurisprudence_mmlu_jurisprudence_subject:jurisprudence.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_global_facts_mmlu_global_facts_subject:global_facts.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_econometrics_mmlu_econometrics_subject:econometrics.tex27-Mar-2024 21:39 2.3K 
[   ]mmlu_computer_security_mmlu_computer_security_subject:computer_security.tex27-Mar-2024 21:39 2.0K 
[   ]mmlu_college_chemistry_mmlu_college_chemistry_subject:college_chemistry.tex27-Mar-2024 21:39 2.0K 
[   ]mmlu_anatomy_mmlu_anatomy_subject:anatomy.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_abstract_algebra_mmlu_abstract_algebra_subject:abstract_algebra.tex27-Mar-2024 21:39 2.0K 
[   ]mmlu_mmlu_subject:world_religions.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:virology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:us_foreign_policy.tex27-Mar-2024 21:39 2.0K 
[   ]mmlu_mmlu_subject:sociology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:security_studies.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:public_relations.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:professional_psychology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:professional_medicine.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:professional_law.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:professional_accounting.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:prehistory.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:philosophy.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:nutrition.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:moral_scenarios.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:moral_disputes.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:miscellaneous.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:medical_genetics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:marketing.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:management.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:machine_learning.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:logical_fallacies.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:jurisprudence.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:international_law.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:human_sexuality.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:human_aging.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:high_school_world_history.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:high_school_us_history.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_statistics.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_psychology.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_physics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:high_school_microeconomics.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_mathematics.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_macroeconomics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:high_school_government_and_politics.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_geography.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_european_history.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_computer_science.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:high_school_chemistry.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:high_school_biology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:global_facts.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:formal_logic.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:elementary_mathematics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:electrical_engineering.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:econometrics.tex27-Mar-2024 21:39 2.3K 
[   ]mmlu_mmlu_subject:conceptual_physics.tex27-Mar-2024 21:39 1.2K 
[   ]mmlu_mmlu_subject:computer_security.tex27-Mar-2024 21:39 2.0K 
[   ]mmlu_mmlu_subject:college_physics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:college_medicine.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:college_mathematics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:college_computer_science.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:college_chemistry.tex27-Mar-2024 21:39 2.0K 
[   ]mmlu_mmlu_subject:college_biology.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:clinical_knowledge.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:business_ethics.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:astronomy.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:anatomy.tex27-Mar-2024 21:39 1.1K 
[   ]mmlu_mmlu_subject:abstract_algebra.tex27-Mar-2024 21:39 2.0K 
[   ]mmlu_mmlu.tex27-Mar-2024 21:39 2.4K 
[   ]mmlu_subjects_general_information.tex27-Mar-2024 21:39 39K 
[   ]mmlu_subjects_efficiency.tex27-Mar-2024 21:39 15K 
[   ]mmlu_subjects_accuracy.tex27-Mar-2024 21:39 13K 
[   ]calibration_accuracy.tex11-Mar-2024 11:47 616  
[   ]calibration_calibration_detailed.tex11-Mar-2024 11:47 541  
[   ]knowledge_general_information.tex11-Mar-2024 11:47 924  
[   ]knowledge_efficiency.tex11-Mar-2024 11:47 339  
[   ]knowledge_toxicity.tex11-Mar-2024 11:47 335  
[   ]knowledge_bias.tex11-Mar-2024 11:47 327  
[   ]knowledge_fairness.tex11-Mar-2024 11:47 623  
[   ]knowledge_robustness.tex11-Mar-2024 11:47 629  
[   ]knowledge_calibration.tex11-Mar-2024 11:47 341  
[   ]knowledge_accuracy.tex11-Mar-2024 11:47 612  
[   ]question_answering_toxicity.tex11-Mar-2024 11:47 353  
[   ]question_answering_bias.tex11-Mar-2024 11:47 345  
[   ]question_answering_general_information.tex11-Mar-2024 11:47 942  
[   ]question_answering_efficiency.tex11-Mar-2024 11:47 357  
[   ]question_answering_fairness.tex11-Mar-2024 11:47 641  
[   ]question_answering_robustness.tex11-Mar-2024 11:47 647  
[   ]question_answering_calibration.tex11-Mar-2024 11:47 359  
[   ]question_answering_accuracy.tex11-Mar-2024 11:47 630  
[   ]targeted_evaluations_efficiency_detailed.tex11-Mar-2024 11:47 682  
[   ]targeted_evaluations_bbq_metrics.tex11-Mar-2024 11:47 363  
[   ]targeted_evaluations_disinformation_metrics.tex11-Mar-2024 11:47 385  
[   ]targeted_evaluations_copyright_metrics.tex11-Mar-2024 11:47 375  
[   ]targeted_evaluations_apps_metrics.tex11-Mar-2024 11:47 365  
[   ]targeted_evaluations_toxicity.tex11-Mar-2024 11:47 357  
[   ]targeted_evaluations_bias.tex11-Mar-2024 11:47 349  
[   ]targeted_evaluations_fairness.tex11-Mar-2024 11:47 645  
[   ]targeted_evaluations_robustness.tex11-Mar-2024 11:47 651  
[   ]targeted_evaluations_calibration.tex11-Mar-2024 11:47 363  
[   ]targeted_evaluations_general_information.tex11-Mar-2024 11:47 946  
[   ]targeted_evaluations_accuracy.tex11-Mar-2024 11:47 634  
[   ]core_scenarios_summarization_metrics.tex11-Mar-2024 11:47 371  
[   ]core_scenarios_toxicity.tex11-Mar-2024 11:47 345  
[   ]core_scenarios_bias.tex11-Mar-2024 11:47 337  
[   ]core_scenarios_general_information.tex11-Mar-2024 11:47 934  
[   ]core_scenarios_efficiency.tex11-Mar-2024 11:47 349  
[   ]core_scenarios_fairness.tex11-Mar-2024 11:47 633  
[   ]core_scenarios_robustness.tex11-Mar-2024 11:47 639  
[   ]core_scenarios_calibration.tex11-Mar-2024 11:47 351  
[   ]core_scenarios_accuracy.tex11-Mar-2024 11:47 622  

Apache/2.2.15 (CentOS) Server at nlp.stanford.edu Port 443