MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs

TL;DR

This paper introduces MHSA, a lightweight framework that mitigates hallucinations in large vision-language models by correcting cross-modal attention patterns without altering the original model parameters.

Contribution

MHSA extends cross-modal attention from detection to mitigation of hallucinations, using a simple MLP to produce corrected attention during inference.

Findings

MHSA effectively reduces hallucinations across various datasets and LVLMs.

Replacing original attention with corrected attention improves model reliability.

The framework does not require modifying existing LVLM parameters.

Abstract

Large vision-language models (LVLMs) have achieved remarkable performance across diverse multimodal tasks, yet they continue to suffer from hallucinations, generating content that is inconsistent with the visual input. Prior work DHCP (Detecting Hallucinations by Cross-modal Attention Pattern) has explored hallucination detection from the perspective of cross-modal attention, but does not address hallucination mitigation. In this paper, we propose MHSA (Mitigating Hallucinations via Steered Attention), a lightweight framework that mitigates hallucinations by learning to correct cross-modal attention patterns in LVLMs. MHSA trains a simple three-layer MLP generator to produce corrected attention, guided by supervisory signals from the DHCP discriminator and the LVLM itself. During inference, MHSA mitigates both discriminative and generative hallucinations across various datasets and LVLMs by simply replacing the original cross-modal attention with the corrected one, without modifying any LVLM parameters. By extending cross-modal attention mechanisms from hallucination detection to hallucination mitigation, MHSA offers a novel perspective on hallucination research in LVLMs and helps enhance their reliability.