3 papers
cs.CV2026
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Chengsheng Zhang, Chenghao Sun, Xinyan Jiang +2
Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined by hallucinations, i.e., the…
cs.LG2026
Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
Xinyan Jiang, Wenjing Yu, Di Wang +1
Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from stat…
cs.CL2025
HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models
Xinyan Jiang, Hang Ye, Yongxin Zhu +3
Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. We introduce HICD, a novel method designed to…