Metraipolis › archive › dc_aeb221c73ef7
What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering — arXiv:2608.14841
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14841
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:08:08.877Z
- SHA-256 of the archived text
40575ee91e3f2ce68b2afbc97f41a825af94392d0c0f18268194fc14f1574d66- Stable URL of this page
https://metraipolis.com/documento/dc_aeb221c73ef7
How to cite
What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering — arXiv:2608.14841 — arXiv (en), https://arxiv.org/abs/2608.14841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aeb221c73ef7 (Metraipolis archive dc_aeb221c73ef7, sha256 40575ee91e3f2ce68b2afbc97f41a825af94392d0c0f18268194fc14f1574d66)
BibTeX
@misc{dcaeb221c73ef7,
title = {What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering — arXiv:2608.14841},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14841},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aeb221c73ef7; sha256 40575ee91e3f2ce68b2afbc97f41a825af94392d0c0f18268194fc14f1574d66},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines. In our setting, the bottleneck shifts from retrieval recall to reranker-side evidence selection: on MMLongBench-Doc, BGE-M3 reaches Recall@20 = 0.86 but only F1@5 = 0.254, and even the visual retriever ColPali reaches only F1@5 = 0.332; a text-only rerank LLM seeing only raw snippets misses table, chart, and layout evidence even when the upstream retriever encoded images. We propose Trident, with two complementary components: Trident-R, a retriever-agnostic LLM reranker that converts each candidate into an LLM-readable semantic record, including a visual caption, section path, entity tags, multi-axis concept hits, and a text snippet, then performs a single adaptive-K rerank call; and Trident-S, a generation-side module that prompts the VLM under topical, entity, and structural lenses before synthesis. On two long-document datasets, the annotation+rerank protocol substantially improves retrieval F1 across five heterogeneous pools, with every reranked pool exceeding the strongest adaptive-K baseline PageIndex. An LLM rerank without the annotation barely changes first-hit ranking, indicating the lift comes from the structured annotation. Trident-S targets open-ended synthesis questions by design, adding up to 6.6 points in generation accuracy on these questions. The best Trident configuration is the strongest downstream QA pipeline in our evaluation, with rankings consistent across two LLM judges (kappa = 0.913). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.14841 — 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 2026-10-18T16:29:13.741Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).