ai safety

Intersectionality in AI Safety: Using Multilevel Models to Understand Diverse Perceptions of Safety in Conversational AI COLING 2024 Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis EMNLP 2024 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NeurIPS 2024 Language Agents: Foundations, Prospects, and Risks EMNLP 2024 Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks EMNLP 2024 Large Language Models Must Be Taught to Know What They Don’t Know NeurIPS 2024 Learning Human-like Representations to Enable Learning Human Values NeurIPS 2024 LLM Evaluators Recognize and Favor Their Own Generations NeurIPS 2024 Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs NeurIPS 2024 Moral Foundations of Large Language Models EMNLP 2024 Multilingual Jailbreak Challenges in Large Language Models ICLR 2024 Negative Human Rights as a Basis for Long-term AI Safety and Regulation (Abstract Reprint) IJCAI 2024 OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research JMLR 2024 On scalable oversight with weak LLMs judging strong LLMs NeurIPS 2024 Position: Technical Research and Talent is Needed for Effective AI Governance ICML 2024 Provable Editing of Deep Neural Networks using Parametric Linear Relaxation NeurIPS 2024 PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails ACL 2024 PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety ACL 2024 RAIN: Your Language Models Can Align Themselves without Finetuning ICLR 2024 Relying on the Unreliable: The Impact of Language Models’ Reluctance to Express Uncertainty ACL 2024 ReMoDetect: Reward Models Recognize Aligned LLM's Generations NeurIPS 2024 Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks NeurIPS 2024 Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? NeurIPS 2024 Secret Collusion among AI Agents: Multi-Agent Deception via Steganography NeurIPS 2024 Sharpness-Aware Data Poisoning Attack ICLR 2024