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

The paper introduces Self-RefineVQA, a training‑free, inference‑time framework that lets a single Vision‑Language Model iteratively generate, critique, and refine its own answers for table visual question answering. By forming a closed self‑feedback loop guided by prompts, the method corrects common reasoning errors such as spatial misalignment and logical hallucinations without requiring additional labeled data or model updates. Experiments on tabular VQA benchmarks show consistent accuracy gains across monolingual and cross‑lingual settings, especially for lightweight models, while keeping inference cost linear and eliminating the need for expensive supervised fine‑tuning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• nlp
• fine-tuning
• multimodal
• benchmarks
• safety