Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models

2026-09-15

AI Summary

本文提出AREA方法，通过自适应分配视觉和文本证据来解决多模态大语言模型在回答知识密集型视觉问题时忽略相关证据的问题。

Abstract

Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved from external sources. However, MLLMs may overlook relevant evidence in both modalities, attending weakly to the textual sentences or visual regions needed for the correct answer. Recent efforts address this by highlighting retrieved text and marking visual regions before generation, but apply a fixed, one-shot policy that cannot adapt to three sources of variation: whether highlighting is necessary, how much evidence different examples require, and when different textual evidence becomes relevant as the answer unfolds. We introduce Adaptive Relevance-guided Evidence Allocation (AREA), a training-free inference-time method that formulates evidence highlighting as adaptive allocation. AREA generates a single probe token to read visual and textual relevance from fixed backbone layers, then makes three decisions: i) whether to intervene (controlled by natural attention coverage and visual sink contamination), ii) how much evidence to expose (determined by relevance entropy), and iii) when to refresh text during generation (triggered by causal context-attention peaks). Across four KB-VQA and seven standard multimodal benchmarks with nine frozen MLLM checkpoints, establishes the best performance among training-free highlighting methods.

Problem

• Multimodal Large Language Models
• Evidence Selection
• Adaptive Allocation

Innovation

• Adaptive Relevance-guided Evidence Allocation
• evidence highlighting
• inference-time method
• multimodal large language models