AI Safety

LORE: Continual Logit Rewriting Fosters Faithful Generation EMNLP 2025 LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion ACL 2025 M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs ACL 2025 Machine Unlearning Fails to Remove Data Poisoning Attacks ICLR 2025 MAGI: Multi-Agent Guided Interview for Psychiatric Assessment ACL 2025 Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization EMNLP 2025 MALTO at SemEval-2025 Task 3: Detecting Hallucinations in LLMs via Uncertainty Quantification and Larger Model Validation SemEval 2025 MALTO at SemEval-2025 Task 4: Dual Teachers for Unlearning Sensitive Content in LLMs SemEval 2025 MAP: Multi-Human-Value Alignment Palette ICLR 2025 MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures - A Comprehensive Framework EMNLP 2025 Mātṛkā: Multilingual Jailbreak Evaluation of Open-Source Large Language Models AACL 2025 MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol EMNLP 2025 Mean Aggregator is More Robust than Robust Aggregators under Label Poisoning Attacks on Distributed Heterogeneous Data JMLR 2025 Measuring Error Alignment for Decision-Making Systems AAAI 2025 Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models AAAI 2025 Measuring Sycophancy of Language Models in Multi-turn Dialogues EMNLP 2025 Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization ICML 2025 Med-CoDE: Medical Critique based Disagreement Evaluation Framework NAACL 2025 Medical MLLM Is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models AAAI 2025 MEGen: Generative Backdoor into Large Language Models via Model Editing ACL 2025 Meme Trojan: Backdoor Attacks Against Hateful Meme Detection via Cross-Modal Triggers AAAI 2025 ME: Modelling Ethical Values for Value Alignment AAAI 2025 MEraser: An Effective Fingerprint Erasure Approach for Large Language Models ACL 2025 Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging EMNLP 2025 MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time NAACL 2025