Metraipolis › archive › dc_d5ba087745df

Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models? — arXiv:2608.07006

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07006
License (as archived)
CC0-1.0
Archived
2026-10-19T09:46:57.289Z
SHA-256 of the archived text
31632ea81496fe365bd8a84d29683a3f64de4554349b0b66dd816a921daa4d61
Stable URL of this page
https://metraipolis.com/documento/dc_d5ba087745df

How to cite

Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models? — arXiv:2608.07006 — arXiv (en), https://arxiv.org/abs/2608.07006 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5ba087745df (Metraipolis archive dc_d5ba087745df, sha256 31632ea81496fe365bd8a84d29683a3f64de4554349b0b66dd816a921daa4d61)
BibTeX
@misc{dcd5ba087745df,
  title = {Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models? — arXiv:2608.07006},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07006},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5ba087745df; sha256 31632ea81496fe365bd8a84d29683a3f64de4554349b0b66dd816a921daa4d61},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07006. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual retrieval-augmented generation (RAG) commonly expands the retrieved evidence set to improve answer-page coverage, implicitly assuming that all available evidence should be passed to the generator. We show that this assumption does not hold for diffusion language models (DLMs): retrieving more pages increases answer-page recall, whereas unconditionally passing all retrieved pages to the generator often reduces answer accuracy, primarily because of semantic conflict. A latent-source analysis explains this mismatch through source-coherence loss in parallel denoising, where position-wise proposals can combine incompatible visual sources into unsupported answers. We further find that such interference is already visible in the first-step answer-block distribution, making it possible to assess evidence before decoding. To preserve retrieval coverage while limiting harmful visual exposure, we propose the Entropy-Based Candidate Filter (ECF), a training-free evidence-admission framework. To reduce irrelevant content within individual candidates, ECF constructs multi-granularity evidence units; to identify beneficial additional evidence, it uses blank-controlled block confidence and retrieval rank to determine whether and which candidate should enter the final context. Across three multimodal DLMs and five visual QA benchmarks, ECF improves answer accuracy by 2.62 percentage points on average over the strongest fixed top-$k$ input and, with LLaDA2.0-Uni, by 2.37 percentage points on average over the best competing training-free result for each dataset. These results show that broader retrieval benefits visual DLM-RAG through selective evidence admission rather than unconditional evidence expansion. Code is publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.07006 — 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 2026-10-19T09:46:37.234Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).