共计 146 篇文章
2026
CRoPS： A Training-Free Hallucination Mitigation Framework for Vision-Language Models
REVIS：Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
microgpt
Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
FraudShield： Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
TraceDet： Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
Hallucination Begins Where Saliency Drops
REACT：SYNERGIZING REASONING AND ACTING IN LANGUAGE MODELS
RAGLens： Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
Why Steering Works：Toward a Unified View of Language Model Parameter Dynamics