Metraipolis › archive › dc_acf04953afca

Less Is More: Graph-free Multimodal RAG via Multi-signal Late Fusion — arXiv:2609.19417

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19417
License (as archived)
CC0-1.0
Archived
2026-10-10T03:48:01.963Z
SHA-256 of the archived text
13bc91e5691d83cdf0fb11c95011856d9b0d0175c19c11f03ec2827f16d8cd7c
Stable URL of this page
https://metraipolis.com/documento/dc_acf04953afca

How to cite

Less Is More: Graph-free Multimodal RAG via Multi-signal Late Fusion — arXiv:2609.19417 — arXiv (en), https://arxiv.org/abs/2609.19417 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_acf04953afca (Metraipolis archive dc_acf04953afca, sha256 13bc91e5691d83cdf0fb11c95011856d9b0d0175c19c11f03ec2827f16d8cd7c)
BibTeX
@misc{dcacf04953afca,
  title = {Less Is More: Graph-free Multimodal RAG via Multi-signal Late Fusion — arXiv:2609.19417},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19417},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_acf04953afca; sha256 13bc91e5691d83cdf0fb11c95011856d9b0d0175c19c11f03ec2827f16d8cd7c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19417. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph-based retrieval-augmented generation (RAG) is widely used for multimodal, cross-document question answering. However, building corpus-level graphs is expensive, slow to query, and difficult to maintain. We present TrioRAG, a graph-free multimodal framework that integrates evidence from three complementary signals: the question, the anchor image, and a VLM-enhanced query generated from both. Each signal retrieves independently over a shared multi-vector index of page text and page images, and the results are combined through late fusion. Further, we introduce AutoQA, a multimodal automotive benchmark whose questions are grounded in noisy, web-sourced images rather than clean document-sourced figures. Its questions require reasoning across manuals. We position it as a model-curated testbed rather than a human-validated gold standard. Across three benchmarks, TrioRAG matches or outperforms graph-based systems while reducing total cost and accelerating per-query inference by 1.6-2.3 times. By construction, AutoQA grounds its questions in out-of-corpus web images. In this setting image retrieval reaches only 19.3% document-level recall, while text-derived signals, especially the VLM-enhanced query, keep retrieval robust.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.19417 — 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 2026-10-10T03:24:08.122Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).