AI Safety

Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization ICLR 2025 Superfluous Instruction: Vulnerabilities Stemming from Task-Specific Superficial Expressions in Instruction Templates ACL 2025 Support is All You Need for Certified VAE Training ICLR 2025 Suppressing BGP Zombies with Route Status Transparency NSDI 2025 SURE: Safety Understanding and Reasoning Enhancement for Multimodal Large Language Models EMNLP 2025 Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation ICLR 2025 Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs IJCNLP 2025 SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use NAACL 2025 Swushroomsia at SemEval-2025 Task 3: Probing LLMs’ Collective Intelligence for Multilingual Hallucination Detection SemEval 2025 Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories EMNLP 2025 System Prompt Hijacking via Permutation Triggers in LLM Supply Chains ACL 2025 Taming Overconfidence in LLMs: Reward Calibration in RLHF ICLR 2025 Tamper-Resistant Safeguards for Open-Weight LLMs ICLR 2025 Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers AAAI 2025 Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals ACL 2025 Teaching Models to Balance Resisting and Accepting Persuasion NAACL 2025 Team Cantharellus at SemEval-2025 Task 3: Hallucination Span Detection with Fine Tuning on Weakly Supervised Synthetic Data SemEval 2025 Tell me about yourself: LLMs are aware of their learned behaviors ICLR 2025 TempParaphraser: “Heating Up” Text to Evade AI-Text Detection through Paraphrasing EMNLP 2025 Test-Time Backdoor Detection for Object Detection Models CVPR 2025 Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations NAACL 2025 Test-Time Multimodal Backdoor Detection by Contrastive Prompting ICML 2025 Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints AAAI 2025 Textual Unlearning Gives a False Sense of Unlearning ICML 2025 The AI Race: Why Current Neural Network-based Architectures are a Poor Basis for Artificial General Intelligence AAAI 2025