共计 214 篇文章
2026
RAGLens： Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
Why Steering Works：Toward a Unified View of Language Model Parameter Dynamics
LLM-VA： Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
AlphaSteer： Learning Refusal Steering with Principled Null-Space Constraint
FRAUDAR： Bounding Graph Fraud in the Face of Camouflage
DiffuGuard： How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs
RelayLLM： Efficient Reasoning via Collaborative Decoding
mHC：流形约束的超连接
Text-to-LoRA： Instant Transformer Adaption