Structured LaTeX encoding of OCR text, combined with document images, improves DocQA accuracy across four MLLMs and four benchmarks without any training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Structured Attention Matters to Multimodal LLMs in Document Understanding
Structured LaTeX encoding of OCR text, combined with document images, improves DocQA accuracy across four MLLMs and four benchmarks without any training.