What Color Is It? A Text-Interference Multimodal Hallucination Benchmark
This addresses a specific hallucination risk in MLMs for researchers and developers, but it is incremental as it focuses on a narrow aspect of a known issue.
The paper tackles the problem of color perception hallucinations in Multimodal Large Models (MLMs) due to informational interference, introducing the 'What Color Is It' benchmark to validate this and explore solutions for improved robustness.
With the rapid advancement of Large Models, numerous text-and-vision-fused Multimodal Large Models (MLMs) have emerged. However, these MLMs remain susceptible to informational interference in visual perception, particularly in color perception, which introduces an additional risk of hallucination. To validate this hypothesis, we introduce the "What Color Is It" dataset, a novel benchmark constructed using a simple method to trigger single-modality visual hallucination in MLMs. Based on this dataset, we further investigate the underlying causes of hallucination in the visual modality of MLMs and propose potential solutions to enhance their robustness.