Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
This addresses a critical limitation for practical applications of LVLMs by reducing hallucinations, though it is an incremental improvement on existing methods.
The paper tackles the problem of hallucinatory text responses in Large Vision-Language Models (LVLMs) by introducing a training-free algorithm called self-correcting Decoding with Generative Feedback (DeGF), which uses text-to-image generative models to provide feedback during decoding, resulting in consistent improvements over state-of-the-art methods across six benchmarks.
While recent Large Vision-Language Models (LVLMs) have shown remarkable performance in multi-modal tasks, they are prone to generating hallucinatory text responses that do not align with the given visual input, which restricts their practical applicability in real-world scenarios. In this work, inspired by the observation that the text-to-image generation process is the inverse of image-conditioned response generation in LVLMs, we explore the potential of leveraging text-to-image generative models to assist in mitigating hallucinations in LVLMs. We discover that generative models can offer valuable self-feedback for mitigating hallucinations at both the response and token levels. Building on this insight, we introduce self-correcting Decoding with Generative Feedback (DeGF), a novel training-free algorithm that incorporates feedback from text-to-image generative models into the decoding process to effectively mitigate hallucinations in LVLMs. Specifically, DeGF generates an image from the initial response produced by LVLMs, which acts as an auxiliary visual reference and provides self-feedback to verify and correct the initial response through complementary or contrastive decoding. Extensive experimental results validate the effectiveness of our approach in mitigating diverse types of hallucinations, consistently surpassing state-of-the-art methods across six benchmarks. Code is available at https://github.com/zhangce01/DeGF.