Owain Evans
Publications by Year
Research Areas
Topic Modeling, Adversarial Robustness in Machine Learning, Natural Language Processing Techniques, Reinforcement Learning in Robotics, Explainable Artificial Intelligence (XAI)
Most-Cited Works
- → Viewpoint: When Will AI Exceed Human Performance? Evidence from AI Experts(2018)538 cited
- → The malicious use of artificial intelligence: Forecasting, prevention, and mitigation(2018)525 cited
- → TruthfulQA: Measuring How Models Mimic Human Falsehoods(2022)492 cited
- → When Will AI Exceed Human Performance? Evidence from AI Experts(2017)222 cited
- Help or Hinder: Bayesian Models of Social Goal Inference(2009)
- → Trial without Error: Towards Safe Reinforcement Learning via Human Intervention(2017)110 cited
- → Learning the Preferences of Ignorant, Inconsistent Agents(2016)86 cited