ChartRQA

ChartRQA is a dataset designed to evaluate advanced chart reasoning capabilities in vision-language models by providing high-quality, step-by-step reasoning data across diverse chart types and complexity levels.

Papers using ChartRQA (15)

VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought2026EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards2025When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs2025Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner2025RECODE: Reasoning Through Code Generation For Visual Question Answering2025Simple Vision-language Math Reasoning Via Rendered Text2025Cross Domain Evaluation Of Multimodal Chain-of-thought Reasoning Of Different Datasets Into The Amazon Cot Framework2025Wilddoc: How Far Are We From Achieving Comprehensive And Robust Document Understanding In The Wild?2025Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning2025MOVE: A Mixture-of-Vision-Encoders Approach for Domain-Focused Vision-Language Processing2025Graph-Based Multimodal Contrastive Learning for Chart Question Answering2025ChartLlama: A Multimodal LLM for Chart Understanding and Generation2023 · 25 citesEnhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs2023Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale2024