mlsanityData to 14 Oct 2026

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

arXiv 2609.21351 ↗First posted 18 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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 1.5, as well as on the table category of CC-OCR and PureDocBench.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 18 Sep 2026.

Builds on

15 of 24 references.

References · 15

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 400
  3. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 229
  4. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 150
  5. 2021PubTables-1M: Towards comprehensive table extraction from unstructured documentscited by 126
  6. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 87
  7. 2024CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacycited by 81
  8. 2026DeepSeek-OCR 2: Visual Causal Flowcited by 74
  9. 2024Focus Anywhere for Fine-grained Multi-page Document Understandingcited by 62
  10. 2026PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsingcited by 57
  11. 2025olmOCR 2: Unit Test Rewards for Document OCRcited by 47
  12. 2025POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversioncited by 34
3 more
  1. 2025Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsingcited by 17
  2. 2025Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCRcited by 12
  3. 2026Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decodingcited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware Guidance
  2. 2026InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning
  3. 2025Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
  4. 2025Visual-TableQA: Open-Domain Benchmark for Reasoning over Table Images
  5. 2025TABLET: A Large-Scale Dataset for Robust Visual Table Understanding
  6. 2024Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment
  7. 2026When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
  8. 2025MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns