{"slug": "l-etzcross-a-cross-lingual-page-level-benchmark-for-multimodal-retrieval-over", "title": "L\\\"etzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents", "summary": "Researchers introduced L\"etzCross, a benchmark for cross-lingual page-level retrieval over Luxembourgish PDF documents, and found that ColPali-style page-image retrievers outperform OCR-based text-only retrievers across query languages. The benchmark includes queries in English, French, German, and Luxembourgish, and fine-tuning experiments showed that multilingual training including Luxembourgish yields the strongest retrieval performance for Luxembourgish queries.", "body_md": "arXiv:2608.21714v1 Announce Type: new\nAbstract: Recent page-image retrievers such as ColPali have improved retrieval over visually rich documents, yet little is known about how they behave in cross-lingual, low-resource settings. We introduce L\\\"etzCross, a benchmark for cross-lingual page-level retrieval over Luxembourgish PDF documents, with document pages indexed as images and queries provided in English, French, German, and Luxembourgish. The benchmark combines text-focused QA pairs with visually grounded QA pairs, covering both textual and visual retrieval needs in PDF-based RAG. We use L\\\"etzCross to compare OCR-based text-only retrievers with ColPali-style page-image retrievers and find that the latter perform better across query languages in this system-level comparison. We also examine single-language and multilingual fine-tuning. Fine-tuning transfers across query languages, with French yielding the highest mean performance on Luxembourgish queries among the single-language settings. In the multilingual setting, including Luxembourgish gives the strongest results and substantially improves retrieval for Luxembourgish queries.", "url": "https://wpnews.pro/news/l-etzcross-a-cross-lingual-page-level-benchmark-for-multimodal-retrieval-over", "canonical_source": "https://arxiv.org/abs/2608.21714", "published_at": "2026-08-25 04:00:00+00:00", "updated_at": "2026-08-25 04:15:25.783149+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "natural-language-processing", "ai-research"], "entities": ["ColPali", "L\"etzCross"], "alternates": {"html": "https://wpnews.pro/news/l-etzcross-a-cross-lingual-page-level-benchmark-for-multimodal-retrieval-over", "markdown": "https://wpnews.pro/news/l-etzcross-a-cross-lingual-page-level-benchmark-for-multimodal-retrieval-over.md", "text": "https://wpnews.pro/news/l-etzcross-a-cross-lingual-page-level-benchmark-for-multimodal-retrieval-over.txt", "jsonld": "https://wpnews.pro/news/l-etzcross-a-cross-lingual-page-level-benchmark-for-multimodal-retrieval-over.jsonld"}}