CVCLLGFeb 12

Benchmarking Vision-Language Models for French PDF-to-Markdown Conversion

arXiv:2602.11960v11 citationsh-index: 4
Originality Synthesis-oriented
AI Analysis

This addresses document parsing for French in RAG pipelines, but it is incremental as it focuses on benchmarking and evaluation rather than new methods.

The paper tackled PDF-to-Markdown conversion for French documents by introducing a benchmark to evaluate Vision-Language Models, finding that proprietary models showed higher robustness on handwriting and forms, with open-weights systems competitive on standard layouts.

This report evaluates PDF-to-Markdown conversion using recent Vision-Language Models (VLMs) on challenging French documents. Document parsing is a critical step for Retrieval-Augmented Generation (RAG) pipelines, where transcription and layout errors propagate to downstream retrieval and grounding. Existing benchmarks often emphasize English or Chinese and can over-penalize benign formatting and linearization choices (e.g., line breaks, list segmentation, alternative table renderings) that are largely irrelevant for downstream use. We introduce a French-focused benchmark of difficult pages selected via model-disagreement sampling from a corpus of 60{,}000 documents, covering handwritten forms, complex layouts, dense tables, and graphics-rich pages. Evaluation is performed with unit-test-style checks that target concrete failure modes (text presence, reading order, and local table constraints) combined with category-specific normalization designed to discount presentation-only variance. Across 15 models, we observe substantially higher robustness for the strongest proprietary models on handwriting and forms, while several open-weights systems remain competitive on standard printed layouts.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes