Part of International Conference on Representation Learning 2025 (ICLR 2025) Conference
Kaishen Wang, Hengrui Gu, Meijun Gao, Kaixiong Zhou
Large Vision-Language Models (VLMs) exhibit significant potential in multimodal tasks but often struggle with hallucinations—responses that are plausible yet visually ungrounded. In this work, we investigate the layer-wise prediction tendencies of VLMs and conduct an in-depth analysis of their decoding mechanism. We observe that VLMs tend to ``overthink'' during the final stages of decoding, making significant prediction shifts in the last few layers often favoring incorrect results, which leads to a surge in hallucinative outputs. Leveraging this localized pattern, we propose a novel decoding strategy inspired by the momentum analogy used in gradient descent-based optimizers. Our method enforces decoding consistency across layers in an adaptive manner during forward passes—an under-explored approach in existing works. This strategy significantly improves the reliability and performance of VLMs in various multimodal tasks, while introducing only negligible efficiency overhead.