AI Safety

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection ICLR 2025 SEAL: Systematic Error Analysis for Value ALignment AAAI 2025 Seal Your Backdoor with Variational Defense ICCV 2025 SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models AAAI 2025 SecDecoding: Steerable Decoding for Safer LLM Generation EMNLP 2025 Security Attacks on LLM-based Code Completion Tools AAAI 2025 Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models ICLR 2025 Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios EMNLP 2025 Self-Consuming Generative Models with Adversarially Curated Data ICML 2025 Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes NAACL 2025 Self-Generated Critiques Boost Reward Modeling for Language Models NAACL 2025 SELF-PERCEPT: Introspection Improves Large Language Models’ Detection of Multi-Person Mental Manipulation in Conversations ACL 2025 SemanticCamo: Jailbreaking Large Language Models through Semantic Camouflage ACL 2025 SEMINAR: SEMantic InformatioN Augmented JailbReak Attack in LLM ACML 2025 SEMU: Singular Value Decomposition for Efficient Machine Unlearning ICML 2025 Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models ACL 2025 SEPS: A Separability Measure for Robust Unlearning in LLMs EMNLP 2025 SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters NAACL 2025 Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback AAAI 2025 SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains ACL 2025 Sequential Decision Making in Stochastic Games with Incomplete Preferences over Temporal Objectives AAAI 2025 SHA256 at SemEval-2025 Task 4: Selective Amnesia – Constrained Unlearning for Large Language Models via Knowledge Isolation SemEval 2025 Shadow-Activated Backdoor Attacks on Multimodal Large Language Models ACL 2025 Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models ACL 2025 Sheep’s Skin, Wolf’s Deeds: Are LLMs Ready for Metaphorical Implicit Hate Speech? ACL 2025