共计 117 篇文章
2026
Seeing Far and Clearly： Mitigating Hallucinations in MLLMs with Attention Causal Decoding
CAN HETEROGENEOUS LANGUAGE MODELS BE FUSED?
Procedural Knowledge at Scale Improves Reasoning
HALLUCINATION-AWARE INTERMEDIATE REPRESENTATION EDIT IN LARGE VISION-LANGUAGE MODELS
In-Place Test-Time Training
Beyond the Global Scores： Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
EMNLP 2025关于幻觉的论文
SAVE： Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
Neural Uncertainty Principle： A Unified View of Adversarial Fragility and LLM Hallucination
DynHD： Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learnig