← all papers · overview

MAD: Modality-adaptive Decoding For Mitigating Cross-modal Hallucinations In Multimodal Large Language Models

Abstract

Multimodal Large Language Models (MLLMs) suffer from cross-modal hallucinations, where one modality inappropriately influences generation about another, leading to fabricated output. This exposes a more fundamental deficiency in modality-interaction control. To address this, we propose Modality-Adaptive Decoding (MAD), a training-free method that adaptively weights modality-specific decoding branc

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).