Web retrieval-augmented generation (RAG) splits a page into fixed-size text chunks or, in recent visual pipelines, screenshot tiles, and the retrieved item serves at once as the unit of indexing, r...
<p><strong>Tác giả:</strong> Peichun Hua, He Sun, Zirui Zhuang, Qi Qi, Yiming Qiu, Shinan Liu, Yunming Xiao</p>
<p>Web retrieval-augmented generation (RAG) splits a page into fixed-size text chunks or, in recent visual pipelines, screenshot tiles, and the retrieved item serves at once as the unit of indexing, ranking, and reading. We trace answer evidence from source HTML to reader input over the full English Wikipedia and find that this coupling loses evidence in text and screenshot pipelines alike: evidence present in the source page often fails to reach the reader intact, particularly structured conten...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.48550/arxiv.2610.37080" target="_blank" rel="noopener">https://doi.org/10.48550/arxiv.2610.37080</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.48550/arxiv.2610.37080" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
