Pith. sign in

REVIEW 9 cited by

Hierarchical multimodal transformers for Multi-Page DocVQA

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2212.05935 v2 pith:ERJFW4HU submitted 2022-12-07 cs.CV cs.AIcs.CL

Rubèn Tito , Dimosthenis Karatzas , Ernest Valveny This is my paper · ORCID
classification cs.CVcs.AIcs.CL
keywords documentsdocvqamulti-pageanswerhierarchicalinformationmethodquestions
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Hierarchical Evidence-Driven Reasoning for Long Document Understanding

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A hierarchical multimodal RAG pipeline with GRPO-trained multi-page evidence verification and memory-guided iteration improves long-document QA accuracy by ~8% over prior open-source baselines.

  2. EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    EffiVLM-Bench is a benchmark study showing token compression is task- and model-dependent, KV cache methods are more loyal, and parameter compression preserves accuracy better at typical ratios.

  3. InsQABench: Benchmarking Chinese Insurance Domain Question Answering with Large Language Models

    cs.CL 2025-01 conditional novelty 6.0 of 10

    The paper introduces a three-part Chinese insurance QA benchmark and shows that fine-tuning with SQL-ReAct and RAG-ReAct improves open LLM performance on it.

  4. Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Codec-guided sparse patch selection plus a lightweight speak/silent gate yields a 4B streaming VLM that is competitive on static tasks, stronger on video/spatial benchmarks, and much cheaper at inference.

  5. Workload-Aware Caching for Multi-Agent Systems

    cs.AI 2026-06 conditional novelty 5.0 of 10

    A workload-aware score combining recomputation cost, DAG dependency count, and agent invocation frequency outperforms standard eviction policies for multi-agent task-result caching.

  6. MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval

    cs.CL 2025-09 conditional novelty 5.0 of 10

    MoLoRAG boosts multi-page document QA by traversing a page graph and scoring pages with both semantic and VLM-judged logical relevance, improving retrieval and answer accuracy on four benchmarks.

  7. DRISHTIKON: Visual Grounding at Multiple Granularities in Documents

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A combined OCR, LLM, and fuzzy-matching pipeline locates answer spans in document images at block, line, word, and point granularity, with line-level grounding F1 of 69.10 on a new 70-document benchmark.

  8. Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks

    cs.CL 2025-04 conditional novelty 4.0 of 10

    A survey that frames the core problem of LLM evaluation as 'evaluation generalization': finite test sets cannot scale with unbounded model capabilities, and proposes two transitions in evaluation design.

  9. Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends

    cs.CL 2025-01 conditional novelty 3.0 of 10

    A structured overview of question answering over visually rich documents, comparing encoding, vision-only, and multi-page methods, and highlighting comparability issues in existing benchmarks.

Pith tools