AI Safety

Self-contradictory reasoning evaluation and detection EMNLP 2024 Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning ICML 2024 Self-Evolution Fine-Tuning for Policy Optimization EMNLP 2024 SELF-GUARD: Empower the LLM to Safeguard Itself NAACL 2024 Self-Recognition in Language Models EMNLP 2024 Semi-factual Explanations in AI AAAI 2024 SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation NAACL 2024 SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types NeurIPS 2024 Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models NeurIPS 2024 Sharpness-Aware Data Poisoning Attack ICLR 2024 ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors EMNLP 2024 SHINE: Shielding Backdoors in Deep Reinforcement Learning ICML 2024 Simpler Becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora? COLING 2024 Simplifying Constraint Inference with Inverse Reinforcement Learning NeurIPS 2024 SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents NeurIPS 2024 SLM as Guardian: Pioneering AI Safety with Small Language Model EMNLP 2024 Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector EMNLP 2024 Social, Legal, Ethical, Empathetic, and Cultural Rules: Compilation and Reasoning AAAI 2024 SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models AAAI 2024 SoFA: Shielded On-the-fly Alignment via Priority Rule Following ACL 2024 Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space NeurIPS 2024 Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models ACL 2024 Spectral Editing of Activations for Large Language Model Alignment NeurIPS 2024 SpeechGuard: Exploring the Adversarial Robustness of Multi-modal Large Language Models ACL 2024 Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions AAAI 2024