Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation

TL;DR

This paper introduces DeP, a training-free method that reduces hallucinations in multimodal large language models by applying controlled textual perturbations during decoding.

Contribution

DeP offers a novel, training-free approach that mitigates hallucinations through dynamic textual interventions and attention variance analysis during decoding.

Findings

DeP significantly reduces hallucinations across multiple benchmarks.

It improves the stability of visual grounding during decoding.

DeP outperforms existing mitigation methods in various evaluations.

Abstract

Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigation methods either perturb the visual representation and deviate from the natural image distribution, or enforce intrusive manipulations that compromise the model's inherent generative fluency. We introduce a novel perspective that multimodal hallucination manifests as the hypersensitivity of visual grounding to textual phrasing during the decoding phase. Building on this insight, we propose Decoding by Perturbation (DeP), a training-free framework mitigating prior-induced hallucinations via controlled textual interventions. DeP employs a dynamic probe applying multi-level textual perturbations to elicit latent language priors. Leveraging attention variance, it enhances stable evidence regions while suppressing suspicious noise in the feature space. Furthermore, it constructs an interpretable prior drift direction using logits statistics to counteract probability biases from textual co-occurrences. Extensive experiments confirm DeP effectively reduces hallucinations and achieves superior performance across multiple benchmarks.