HII-DPO: Eliminate Hallucination via Accurate Hallucination-Inducing Counterfactual Images
This addresses hallucinations in VLMs, which is a critical issue for reliable multimodal AI applications, though it appears incremental as it builds on existing alignment frameworks.
The paper tackled the problem of hallucinations in Large Vision-Language Models caused by language bias, achieving up to a 38% improvement over state-of-the-art methods on standard hallucination benchmarks.
Large Vision-Language Models (VLMs) have achieved remarkable success across diverse multimodal tasks but remain vulnerable to hallucinations rooted in inherent language bias. Despite recent progress, existing hallucination mitigation methods often overlook the underlying hallucination patterns driven by language bias. In this work, we design a novel pipeline to accurately synthesize Hallucination-Inducing Images (HIIs). Using synthesized HIIs, we reveal a consistent scene-conditioned hallucination pattern: models tend to mention objects that are highly typical of the scene even when visual evidence is removed. To quantify the susceptibility of VLMs to this hallucination pattern, we establish the Masked-Object-Hallucination (MOH) benchmark to rigorously evaluate existing state-of-the-art alignment frameworks. Finally, we leverage HIIs to construct high-quality preference datasets for fine-grained alignment. Experimental results demonstrate that our approach effectively mitigates hallucinations while preserving general model capabilities. Specifically, our method achieves up to a 38% improvement over the current state-of-the-art on standard hallucination benchmarks.