What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering

• URL: http://arxiv.org/abs/2608.14841v1
• Date: Fri, 14 Aug 2026 19:29:42 GMT
• Title: What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering
• Abstract summary: Trident is a visual-question-answering system with a visual caption, section path, entity tags, multi-axis concept hits, and a text snippet.<n>On two long-document datasets, the annotation+rerank protocol substantially improves retrieval F1 across five datasets.<n>The best Trident configuration is the strongest downstream QA pipeline in our evaluation.
• Score: 21.941823782270557
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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).

Related papers

• Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1) [4.198923768732269]
  The MIR Challenge was held at the first EReL@MIR workshop, co-located with The Web Conference 2025.<n>It asked participants to build a emphsingle retrieval system that handles two complementary regimes.<n>This report describes the challenge design, datasets, and evaluation protocol; reports the final standings; and analyses the three winning teams' systems.
  arXiv  Detail & Related papers  (2026-06-02T21:39:32Z)
• MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation [64.33427079838602]
  Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into coherent, attributed text.<n>We present MARQUIS: a three-stage pipeline that addresses these limitations through query expansion, fusion, and reranking.<n>For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems.
  arXiv  Detail & Related papers  (2026-05-17T20:19:04Z)
• UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval [87.12447641908143]
  We propose UniCVR, the first unified zero-shot composed visual retrieval framework.<n>UniCVR jointly addresses all three tasks without any task-specific human-annotated data.<n>In Stage I, we train the MLLM as a compositional query embedder via contrastive learning on a curated dataset of approximately 3.5M samples.<n>In Stage II, we introduce an MLLM-guided dual-level reranking mechanism that applies adaptive budgeted subset scoring to a small number of top-ranked candidates.
  arXiv  Detail & Related papers  (2026-04-22T08:16:50Z)
• MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries [2.756584457554517]
  Map-Disambiguate-Enrich-Reduce (MDER) generates context-derived triple descriptions and integrates them with entity-level summaries.<n>Decompose-Resolve (DR) decomposes user queries into resolvable triples and grounds them in the Knowledge Graph.<n>MDER and DR form an LLM-driven QA pipeline that is robust to sparse, incomplete, and complex relational data.
  arXiv  Detail & Related papers  (2026-03-11T18:38:44Z)
• $G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA [53.491241153213565]
  $G2$-Reader is a dual-graph system for multimodal question answering.<n>$G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)<n>On VisDoMBench across five multimodal domains, $G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)
  arXiv  Detail & Related papers  (2026-01-29T17:52:54Z)
• Beyond Patch Aggregation: 3-Pass Pyramid Indexing for Vision-Enhanced Document Retrieval [0.0]
  Document centric RAG pipelines usually begin with OCR, followed by brittles for chunking, table parsing, and layout reconstruction.<n>We introduce VisionRAG, a multimodal retrieval system that is OCR free and model agnostic.<n> VisionRAG indexes documents directly as images, preserving layout, tables, and spatial cues, and builds semantic vectors without committing to a specific extraction.
  arXiv  Detail & Related papers  (2025-11-26T07:18:06Z)
• Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval [68.71038700559195]
  Chain of Retrieval(COR) is a novel iterative framework for full-paper retrieval.<n>We present SCIBENCH, a benchmark providing both complete and segmented contexts of full papers for queries and candidates.
  arXiv  Detail & Related papers  (2025-07-14T08:41:53Z)
• MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models [22.50450558103786]
  In a real-world RAG system, the current query often involves spoken ellipses and ambiguous references from dialogue contexts.<n>We propose a novel query rewriting method MaFeRw, which improves RAG performance by integrating multi-aspect feedback from both the retrieval process and generated results.<n> Experimental results on two conversational RAG datasets demonstrate that MaFeRw achieves superior generation metrics and more stable training compared to baselines.
  arXiv  Detail & Related papers  (2024-08-30T07:57:30Z)
• SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs [85.54906813106683]
  We propose a simple yet effective framework to enhance open-domain question answering (ODQA) with large language models (LLMs) SuRe helps LLMs predict more accurate answers for a given question, which are well-supported by the summarized retrieval (SuRe) Experimental results on diverse ODQA benchmarks demonstrate the superiority of SuRe, with improvements of up to 4.6% in exact match (EM) and 4.0% in F1 score over standard prompting approaches.
  arXiv  Detail & Related papers  (2024-04-17T01:15:54Z)
• Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval [51.437420003471615]
  We propose the Retrieval-Pretrained Transformer (RPT), an architecture and training procedure for jointly training a retrieval-augmented LM from scratch. RPT improves retrieval quality and subsequently perplexity across the board compared to strong baselines.
  arXiv  Detail & Related papers  (2023-06-23T10:18:02Z)
• Visconde: Multi-document QA with GPT-3 and Neural Reranking [4.9069311006119865]
  This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple documents. The system, called Visconde, uses a three-step pipeline to perform the task: decompose, retrieve, and aggregate.
  arXiv  Detail & Related papers  (2022-12-19T17:39:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.