AI Safety

Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models ICML 2025 Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary EMNLP 2025 Understanding How Value Neurons Shape the Generation of Specified Values in LLMs EMNLP 2025 Understanding Large Language Model Vulnerabilities to Social Bias Attacks ACL 2025 Understanding Refusal in Language Models with Sparse Autoencoders EMNLP 2025 Understanding the Dark Side of LLMs’ Intrinsic Self-Correction ACL 2025 Understanding the Logic of Direct Preference Alignment through Logic ICML 2025 Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights ACL 2025 Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization ICLR 2025 Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs EMNLP 2025 Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation ACL 2025 Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning ICLR 2025 Unlearning vs. Obfuscation: Are We Truly Removing Knowledge? EMNLP 2025 Unlocking LLM Safeguards for Low-Resource Languages via Reasoning and Alignment with Minimal Training Data EMNLP 2025 Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering EMNLP 2025 Unmasking Fake Careers: Detecting Machine-Generated Career Trajectories via Multi-layer Heterogeneous Graphs EMNLP 2025 Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models ACL 2025 Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models ACL 2025 Unraveling Misinformation Propagation in LLM Reasoning EMNLP 2025 Unraveling the Mystery: Defending Against Jailbreak Attacks Via Unearthing Real Intention COLING 2025 UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases IJCNLP 2025 Using Humor to Bypass Safety Guardrails in Large Language Models ACL 2025 UTF: Under-trained Tokens as Fingerprints —— a Novel Approach to LLM Identification ACL 2025 UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV Mapping ICLR 2025 VAGUE‐Gate: Plug‐and‐Play Local‐Privacy Shield for Retrieval‐Augmented Generation IJCNLP 2025