Metraipolis › archive › dc_3a166f97d116
Pix2Evidence: A Multimodal RAG System for Text and Visual Evidence — arXiv:2610.41335
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41335
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:20:03.708Z
- SHA-256 of the archived text
52cdc711cb8033f944a1c1180047ff605a546c32c91d0e8694e0f4881c3c41ff- Stable URL of this page
https://metraipolis.com/documento/dc_3a166f97d116
How to cite
Pix2Evidence: A Multimodal RAG System for Text and Visual Evidence — arXiv:2610.41335 — arXiv (en), https://arxiv.org/abs/2610.41335 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a166f97d116 (Metraipolis archive dc_3a166f97d116, sha256 52cdc711cb8033f944a1c1180047ff605a546c32c91d0e8694e0f4881c3c41ff)
BibTeX
@misc{dc3a166f97d116,
title = {Pix2Evidence: A Multimodal RAG System for Text and Visual Evidence — arXiv:2610.41335},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41335},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a166f97d116; sha256 52cdc711cb8033f944a1c1180047ff605a546c32c91d0e8694e0f4881c3c41ff},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41335. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented generation (RAG) over visually rich documents must find both relevant content and the evidence that supports an answer. Screenshot retrieval preserves images and page structure, but written facts within screenshots also need to be searchable. Moreover, topical relevance alone does not identify which retrieved tile contains evidence for the answer. We introduce Pix2Evidence, a multimodal RAG system that encodes each screenshot tile together with its available transcription into a single fused image--text representation, so that layout and readable text are considered jointly during retrieval. To guide evidence selection, a vision-language teacher describes the visible content that supports each training question. We use these descriptions to adapt the retriever, then rerank the retrieved candidates before answer generation. Extensive experiments demonstrate that Pix2Evidence outperforms state-of-the-art methods. Across five widely-used Wikipedia QA benchmarks, the non-reranked Pix2Evidence leads the main comparison in answer accuracy on four. On MMSearch, it reaches 26.0\%, 4.4 percentage points above PixelRAG. We will release the code and share derived data where licensing and privacy reviews permit. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2610.41335 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T08:06:23.748Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).