SOTAVerified

Ethics

Papers

Showing 826832 of 832 papers

TitleStatusHype
Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and ClaudeCode0
Towards Effective Paraphrasing for Information DisguiseCode0
MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active LearningCode0
Towards Empathic Deep Q-LearningCode0
Defining a Sandbox for Responsible AICode0
Edu-Values: Towards Evaluating the Chinese Education Values of Large Language ModelsCode0
TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty SimulationsCode0
Show:102550
← PrevPage 34 of 34Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RuGPT-3 LargeAccuracy68.6Unverified
2RuGPT-3 MeduimAccuracy68.3Unverified
3RuGPT-3 SmallAccuracy55.5Unverified
4Human benchmarkAccuracy52.9Unverified
#ModelMetricClaimedVerifiedStatus
1Human benchmarkAccuracy67.6Unverified
2RuGPT-3 SmallAccuracy60.9Unverified
3RuGPT-3 LargeAccuracy44.9Unverified
4RuGPT-3 MediumAccuracy44.1Unverified