AI RESEARCH
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
arXiv CS.CL
•
ArXi:2603.09095v1 Announce Type: new Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven MLLMs across seven benchmarks in five input modes, spanning both synthetically rendered text and realistic document images from arXi PDFs to Wikipedia pages. We find that the modality gap is task- and data-dependent.