ai safety

On the Exploitability of Instruction Tuning NeurIPS 2023 RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms EMNLP 2023 Regulation and NLP (RegNLP): Taming Large Language Models EMNLP 2023 SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created through Human-Machine Collaboration ACL 2023 Targeted Knowledge Infusion To Make Conversational AI Explainable and Safe AAAI 2023 Thought Cloning: Learning to Think while Acting by Imitating Human Thinking NeurIPS 2023 Unveiling Safety Vulnerabilities of Large Language Models EMNLP 2023 Adversarial training for high-stakes reliability NeurIPS 2022 Consent as a Foundation for Responsible Autonomy AAAI 2022 Parametrically Retargetable Decision-Makers Tend To Seek Power NeurIPS 2022 Planning to Avoid Side Effects AAAI 2022 Responsible Disclosure of Generative Models Using Scalable Fingerprinting ICLR 2022 Role of Human-AI Interaction in Selective Prediction AAAI 2022 SafeText: A Benchmark for Exploring Physical Safety in Language Models EMNLP 2022 When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment NeurIPS 2022 Adversarial Examples in Physical World IJCAI 2021 Agent Incentives: A Causal Perspective AAAI 2021 Auditing Robot Learning for Safety and Compliance during Deployment CoRL 2021 Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models AAAI 2021 Optimal Policies Tend To Seek Power NeurIPS 2021 Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database AAAI 2021 Reliability Testing for Natural Language Processing Systems ACL 2021 Unifying Principles and Metrics for Safe and Assistive AI AAAI 2021 Asymptotically Unambitious Artificial General Intelligence AAAI 2020 Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents ICLR 2020