2025/06/19 by Chang Liu, Liu, Chang, Hongkai Chen +11 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Multimodal Machine Learning Applications #Text Readability and Simplification #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2506.21600
openalex publication_date 2025/06/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Document understanding remains a significant challenge for multimodal large language models (MLLMs). While previous research has primarily focused on locating evidence pages through precise multimodal queries, our work investigates a fundamental yet overlooked aspect: how input format influences document comprehension performance. Through systematic analysis, we discover that raw OCR text often impairs rather than improves MLLMs' performance, which is a counterintuitive finding we attribute to attention dispersion and structure loss. To further substantiate our hypothesis, we propose a novel structure-preserving approach that encodes document elements using the LaTex paradigm, maintaining the hierarchical organization and spatial relationships critical for comprehension. Our attention analysis reveals that structured text induces structured attention patterns on both textual and visual content, directing models to focus on semantically meaningful regions while reducing attention waste. This approach significantly enhances MLLMs' document question answering performance across diverse document types without requiring architectural modifications or additional training.