conftrace_

ocr noise

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

masked patch prediction (1) synthetic scan generation (1) document digitization (1) pixel-based language model (1) historical document analysis (1) masked image modeling (1) historical document (1) optical character recognition (1) retrieval-augmented generation (1) knowledge base (1)

Papers

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation ICCV 2025 PHD: Pixel-Based Language Modeling of Historical Documents EMNLP 2023