SOURCE-LINKED INTELLIGENCE

GUIDE: Guiding Internal Evidence with Language Instructions

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Large multimodal models follow instructions about what to generate, but not necessarily about what evidence to rely on. Hence, models may continue to depend on shortcut-associated cues even when instructions suggest otherwise. We introduce GUIDE, a framework for controlling internal evidence usage through language instructions. GUIDE combines grouped parameter-efficient adaptation with instruction-conditioned gating to modulate multimodal evidence pathways during reasoning and generation. We further introduce a pathway-level evaluation framework that characterizes instruction-conditioned evide

Read original source ↗ Open in workspace

recordType

paper

region

Global