共计 237 篇文章

---

2026

03-31

EMNLP 2025关于幻觉的论文

03-30

SAVE： Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination

03-28

Neural Uncertainty Principle： A Unified View of Adversarial Fragility and LLM Hallucination

03-27

DynHD： Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learnig

03-23

Attention MoA

03-22

Locate-then-Sparsify： Attribution Guided Sparse Strategy for Visual Hallucination Mitigation

03-17

Fighting Hallucinations with Counterfactuals： Diffusion-Guided Perturbations for LVLM Hallucination Suppression

03-16

Efficient Refusal Ablation in LLM through Optimal Transport

03-13

The Assistant Axis： Situating and Stabilizing the Default Persona of Language Model

03-12

Why LVLMs Are More Prone to Hallucinations in Longer Responses： The Role of Context