Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection (2509.03113v1)

Abstract: Hallucinations in multimodal LLM are caused by the text-visual bias and the co-occurrence bias. The former reflects an over-reliance on text information in the decision-making process, while the latter arises from the statistical object-pairing patterns abstracted from the training data. Existing mitigation methods heuristically address these biases without understanding the fluctuating bias level across the instances. We first propose estimating the influence of respective token types (visual, prompt, and previous outputs) using a gradient-based self-reflection method. The estimated token influence further enables the detection of object-related visual tokens and their integration into an influence-aware contrastive decoding framework to mitigate both types of biases simultaneously. Our method operates without the need for additional resources, such as costly fine-tuning, extra models, or data statistics. Extensive experiments show it effectively reduces hallucinations, achieving up to a 92% accuracy increase on LLaVA-QA90.