2 papers
cs.CV2026
Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification
Han Sun, Qin Li, Peixin Wang +1
Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in hig…
cs.LG2025
DEVAL: A Framework for Evaluating and Improving the Derivation Capability of Large Language Models
Yifan Li, Qin Li, Min Zhang
Assessing the reasoning ability of Large Language Models (LLMs) over data remains an open and pressing research question. Compared with LLMs, human reasoning can derive correspondi…