ai safety

SLM as Guardian: Pioneering AI Safety with Small Language Model EMNLP 2024 SoFA: Shielded On-the-fly Alignment via Priority Rule Following ACL 2024 Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models ACL 2024 STAR: SocioTechnical Approach to Red Teaming Language Models EMNLP 2024 Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections NAACL 2024 Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution EMNLP 2024 The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm EMNLP 2024 “They are uncultured”: Unveiling Covert Harms and Social Threats in LLM Generated Conversations EMNLP 2024 ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages ACL 2024 Towards Healthy AI: Large Language Models Need Therapists Too NAACL 2024 Tree of Attacks: Jailbreaking Black-Box LLMs Automatically NeurIPS 2024 Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks COLING 2024 TrustAgent: Towards Safe and Trustworthy LLM-based Agents EMNLP 2024 Unelicitable Backdoors via Cryptographic Transformer Circuits NeurIPS 2024 Universal Prompt Optimizer for Safe Text-to-Image Generation NAACL 2024 WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models EMNLP 2024 XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models NAACL 2024 Anthropomorphization of AI: Opportunities and Risks EMNLP 2023 Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark ACL 2023 Do Stochastic Parrots have Feelings Too? Improving Neural Detection of Synthetic Text via Emotion Recognition EMNLP 2023 Foundations of Cooperative AI AAAI 2023 Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI ACL 2023 Honesty Is the Best Policy: Defining and Mitigating AI Deception NeurIPS 2023 Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey EACL 2023 Mitigating Adversarial Norm Training with Moral Axioms AAAI 2023