AI Safety

PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning IJCAI 2025 Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models EMNLP 2025 Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study ICML 2025 PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data ICML 2025 PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models NAACL 2025 Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers IJCAI 2025 POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization ICML 2025 Position: AI Safety Must Embrace an Antifragile Perspective ICML 2025 Position: AI Safety should prioritize the Future of Work ICML 2025 Position: Build Agent Advocates, Not Platform Agents ICML 2025 Position: Challenges and Future Directions of Data-Centric AI Alignment ICML 2025 Position: Editing Large Language Models Poses Serious Safety Risks ICML 2025 Position: Humanity Faces Existential Risk from Gradual Disempowerment ICML 2025 Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States ICML 2025 POW: Political Overton Windows of Large Language Models EMNLP 2025 Pragmatic Inference Chain (PIC) Improving LLMs’ Reasoning of Authentic Implicit Toxic Language EMNLP 2025 PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree NAACL 2025 PredictaBoard: Benchmarking LLM Score Predictability ACL 2025 PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement EMNLP 2025 Preference Learning for AI Alignment: a Causal Perspective ICML 2025 Pretend Benign: A Stealthy Adversarial Attack by Exploiting Vulnerabilities in Cooperative Perception ICCV 2025 PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks EMNLP 2025 princi/pal: A Moral Dilemma Tamagotchi Game NeurIPS 2025 Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples ICML 2025 Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents EMNLP 2025