AI Safety

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge EMNLP 2025 Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts ICCV 2025 MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework EMNLP 2025 Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System ACL 2025 Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data ICLR 2025 Mind the (Belief) Gap: Group Identity in the World of LLMs ACL 2025 Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures ACL 2025 Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking CVPR 2025 Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values? EMNLP 2025 Minimalist Concept Erasure in Generative Models ICML 2025 Mirror Minds : An Empirical Study on Detecting LLM-Generated Text via LLMs COLING 2025 MisinfoBench: A Multi-Dimensional Benchmark for Evaluating LLMs’ Resilience to Misinformation EMNLP 2025 Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNets EMNLP 2025 Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality ICLR 2025 Mitigating Paraphrase Attacks on Machine-Text Detection via Paraphrase Inversion ACL 2025 Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization ICLR 2025 Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent Framework AAAI 2025 Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace ICLR 2025 Mixture of insighTful Experts (MoTE): The Synergy of Reasoning Chains and Expert Mixtures in Self-Alignment ACL 2025 ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection AAAI 2025 MLLM-as-a-Judge for Image Safety without Human Labeling CVPR 2025 MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique EMNLP 2025 MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts? EMNLP 2025 Model Equality Testing: Which Model is this API Serving? ICLR 2025 Model Immunization from a Condition Number Perspective ICML 2025