AI Safety

How to Mitigate Overfitting in Weak-to-strong Generalization? ACL 2025 How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation EMNLP 2025 How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts? EMNLP 2025 HPS: Hard Preference Sampling for Human Preference Alignment ICML 2025 Human-AI Moral Judgment Congruence on Real-World Scenarios: A Cross-Lingual Analysis EMNLP 2025 Human Bias in the Face of AI: Examining Human Judgment Against Text Labeled as AI Generated ACL 2025 Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script IJCNLP 2025 Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors ICLR 2025 Human vs. AI: A Novel Benchmark and a Comparative Study on the Detection of Generated Images and the Impact of Prompts COLING 2025 Hyperbolic Safety-Aware Vision-Language Models CVPR 2025 HyperDefender: A Robust Framework for Hyperbolic GNNs AAAI 2025 ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks ICML 2025 IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves ICCV 2025 Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streams AAAI 2025 Idola Tribus of AI: Large Language Models tend to perceive order where none exists EMNLP 2025 IHEval: Evaluating Language Models on Following the Instruction Hierarchy NAACL 2025 I Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text COLING 2025 ImgTrojan: Jailbreaking Vision-Language Models with ONE Image NAACL 2025 Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment CVPR 2025 Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers EMNLP 2025 Improved Techniques for Optimization-Based Jailbreaking on Large Language Models ICLR 2025 Improved Unbiased Watermark for Large Language Models ACL 2025 Improve LLM-as-a-Judge Ability as a General Ability EMNLP 2025 Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors Localization ACL 2025 Improving Alignment in LVLMs with Debiased Self-Judgment EMNLP 2025