Metraipolis › archive › dc_436dc1fd232c

Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images — arXiv:2610.32423

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32423
License (as archived)
CC0-1.0
Archived
2026-10-26T19:51:55.636Z
SHA-256 of the archived text
01790482a53bcf080460e508a7433ad2c836032bfd436a0981d41447b7908a93
Stable URL of this page
https://metraipolis.com/documento/dc_436dc1fd232c

How to cite

Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images — arXiv:2610.32423 — arXiv (en), https://arxiv.org/abs/2610.32423 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_436dc1fd232c (Metraipolis archive dc_436dc1fd232c, sha256 01790482a53bcf080460e508a7433ad2c836032bfd436a0981d41447b7908a93)
BibTeX
@misc{dc436dc1fd232c,
  title = {Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images — arXiv:2610.32423},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32423},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_436dc1fd232c; sha256 01790482a53bcf080460e508a7433ad2c836032bfd436a0981d41447b7908a93},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32423. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in Vision-Language Models (VLMs) have significantly improved Visual Question Answering (VQA) performance, yet their reasoning over structured content such as tables remains inconsistent, often plagued by spatial misalignment and logical hallucinations. Existing approaches for improving table VQA typically rely on architectural modifications or expensive supervised fine-tuning (SFT), which impose high barriers to entry due to the need for large-scale, expert-annotated datasets and significant computational resources. In this work, we propose Self-RefineVQA, a training-free, inference-time self-correction framework that improves table VQA performance without additional labeled data or model updates. Inspired by human revision behavior, our method enables a single VLM to iteratively act as a generator, critic, and refiner, forming a closed self-feedback loop that corrects common reasoning errors through prompt-guided re-evaluation. Experiments on tabular VQA benchmarks demonstrate that Self-RefineVQA yields consistent accuracy gains in monolingual and cross-lingual understanding, with a particularly significant boost for small models, enabling lightweight models (e.g., 2B-7B parameters) to rival the performance of significantly larger counterparts. Furthermore, we provide a comparative complexity analysis demonstrating that while inference cost increases linearly, our framework offers superior data efficiency and a lower cumulative cost by eliminating the prohibitive annotation bottleneck of human labeling required for fine-tuning. Our results highlight the potential of prompt-based self-improvement as a scalable, accessible paradigm for reliable table reasoning in VLMs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.32423 — 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 2026-10-26T19:45:33.412Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).