PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
This addresses hallucinations in MLLMs for dense captioning, offering a new metric and training method, but it is incremental as it builds on existing MLLM frameworks.
The paper tackles the problem of hallucinations in Multimodal Large Language Models for dense image captioning by introducing HalFscore, a novel metric for granular evaluation, and PerturboLLaVA, a training method that uses adversarially perturbed text to reduce reliance on language priors, resulting in improved caption fidelity and outperforming existing approaches on benchmarks.
This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs) particularly for dense image captioning tasks. To tackle the challenge, we identify the current lack of a metric that finely measures the caption quality in concept level. We hereby introduce HalFscore, a novel metric built upon the language graph and is designed to evaluate both the accuracy and completeness of dense captions at a granular level. Additionally, we identify the root cause of hallucination as the model's over-reliance on its language prior. To address this, we propose PerturboLLaVA, which reduces the model's reliance on the language prior by incorporating adversarially perturbed text during training. This method enhances the model's focus on visual inputs, effectively reducing hallucinations and producing accurate, image-grounded descriptions without incurring additional computational overhead. PerturboLLaVA significantly improves the fidelity of generated captions, outperforming existing approaches in handling multimodal hallucinations and achieving improved performance across general multimodal benchmarks.