Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner

To bridge this gap, we propose a benchmark based on a hierarchical design philosophy to evaluate the recognition capabilities of VLLMs in training-free scenarios. It comes from a paper posted to arXiv on 26 October 2026. Pre-trained foundation models have recently made significant progress in table-related tasks such as table understanding and reasoning. However, recognizing the structure and content of unstructured tables using Vision Large Language Models (VLLMs) remains under-explored. Through in-depth evaluations, we find that low-quality image input is a significant bottleneck in the recognition process. Drawing inspiration from this, we propose the Neighbor-Guided Toolchain Reasoner (NGTR) framework, which is characterized by integrating diverse lightweight tools for visual operations aimed at mitigating issues with low-quality images. Specifically, we transfer a tool selection experience from a similar neighbor to the input and design a reflection module to supervise the tool invocation process. Extensive experiments on public datasets demonstrate that our approach significantly enhances the recognition capabilities of the vanilla VLLMs. We believe that the benchmark and framework could provide an alternative solution to table recognition.

Why it counts

To bridge this gap, we propose a benchmark based on a hierarchical design philosophy to evaluate the recognition capabilities of VLLMs in training-free scenarios. We believe that the benchmark and framework could provide an alternative solution to table recognition.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.