The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The paper introduces Loud and Clear (LoC), a method that enhances multimodal document retrieval-augmented generation by fully utilizing visual token capacity and refining retrieved pages to highlight evidence. LoC combines higher-resolution pages with OCR of query-relevant regions, achieving significant accuracy gains over eight prior methods on multiple benchmarks. The study demonstrates that the way retrieved pages are presented to the generator is a critical bottleneck beyond retrieval itself.
The paper introduces a production-ready content‑extraction system tailored for generative AI workloads, addressing the heterogeneity of enterprise data formats such as PDFs, spreadsheets, and scanned documents. It features selective OCR routing, a scarcity‑first curation engine with a reference‑based extraction scorer, a deterministic structure‑aware chunker, and a read‑only retrieval evaluator that generates grounded questions and reports metrics like Hit@k and MRR. On a 180‑document corpus, the system achieves high accuracy (97.4/100 character score, 0.13% error rate) and strong retrieval performance (Hit@1 68.6%, Hit@10 92.8%, MRR 0.77).
The paper introduces a lightweight CPU-based extension to GROBID that uses layout-guided masking to identify figure, table, and paratext regions in scientific PDFs. By routing tokens to specialized GROBID models or discarding them, the method improves structural accuracy on PMC corpora and enhances figure caption recovery. It also achieves competitive table detection and body‑text precision compared to vision‑based GPU parsers while operating entirely on CPU and costing significantly less.
arXiv:2608. 15064v1 Announce Type: new Abstract: Parsing visual documents into machine-readable representations is fundamental to document intelligence.
The paper evaluates how different chunking strategies—fixed-size, recursive paragraph-first, and content-defined—affect the cost of updating embeddings when Wikipedia documents are revised. Using 120 pairs of Chinese and English revisions, the authors find that fixed-size chunking requires the most recomputation (57‑68 % of the workload), while recursive and content-defined chunking need less (38‑56 % and 43‑54 % respectively). Despite these differences, evidence recall under a 2048‑token retrieval budget varies by less than two percentage points across methods and languages.
arXiv:2603. 26815v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems for financial document QA typically follow a chunk-based paradigm: documents are split into fragments, embedded, and retrieved by similarity.