WildTableBench is the first QA benchmark for naturally occurring table images, where 21 multimodal models were evaluated and only one exceeded 50% accuracy.
hub
arXiv preprint arXiv:2404.19205 , year =
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
dataset 2
background 1
citation-polarity summary
representative citing papers
Introduces OCR-Robust benchmark and evaluates 18 VLMs showing clean accuracy does not guarantee robustness with charts and tables more fragile than documents under selected perturbations.
TABVERSE benchmark shows representation format substantially affects LLM and VLM performance on table QA, structural understanding, and reconstruction tasks.
TableVista benchmark finds foundation models maintain performance across visual styles but degrade sharply on complex table structures and vision-only settings.
VT-Bench aggregates 14 datasets from 9 domains and evaluates 23 models to standardize visual-tabular discriminative and generative tasks.
TableVision benchmark shows explicit spatial grounding recovers MLLM reasoning on hierarchical tables, delivering 12.3% accuracy improvement through a decoupled perception-reasoning framework.
Visual-TableQA is a new open-domain benchmark of rendered table images and complex QA pairs created via multi-LLM collaborative generation, with fine-tuned models showing robust generalization to external tests.
OCRBench v2 is a new benchmark with four times more tasks than prior versions that reveals most large multimodal models score below 50 out of 100 on visual text tasks and share five specific weaknesses.
In LVLMs, attention can be replaced by random Gaussian weights with little or no performance loss, indicating that current models get lost in attention rather than efficiently using visual context.
DenTab provides 2,000 annotated dental table images and 2,208 questions to benchmark 16 systems on table structure recognition and VQA, revealing that strong layout recovery does not ensure reliable multi-step arithmetic, and proposes a Table Router Pipeline combining VLMs with rule-based execution.
IAPO is an RL method that aligns model input attributions with a teacher to improve tool-calling in multimodal SLMs, reporting 3% average VQA accuracy gains on Qwen2.5-VL-3B across six tests.
DataArc-SynData-Toolkit is an open-source, configuration-driven framework that unifies synthetic data generation for multimodal, multilingual, and multi-task LLM training with improved usability and quality control.
A survey that categorizes TQA benchmarks and LLM modeling strategies by challenges while identifying underexplored areas such as reinforcement learning.