arXiv cs.CV
· Papers
SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language Models
arXiv:2608.04244v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) make grounded predictions in real-world scenes by combining visual and textual cues, yet existing benchmarks rarely reveal how they arbitrate between these evidence sources when they conflict. We introduce SIGNPOST-Bench, a control