SOURCE-LINKED INTELLIGENCE

PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Table extraction suffers from frequent structural errors and semantic hallucinations. We propose PrismAlign, a multi-VLM framework aligning diverse visual perspectives to resolve ambiguity. It integrates priors of table logic to assess output plausibility, decoupling structural alignment from cell content alignment. A Bayesian decision strategy maximizes alignment accuracy by exploiting the correlation between extraction errors and computable rule violations. Evaluated on open-source and custom VLMs, PrismAlign reduces hallucinations and achieves state-of-the-art performance on OmniDocBench 1.

Read original source ↗ Open in workspace

recordType

paper

region

Global