ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908999281016832 |
|---|---|
| author | Liu, Zheng Lin, Honglin Qin, Chonghan Wang, Xiaoyang Gao, Xin Li, Yu Cai, Mengzhang Zhu, Yun Zhong, Zhanping Pei, Qizhi Pan, Zhuoshi Shang, Xiaoran Cui, Bin He, Conghui Zhang, Wentao Wu, Lijun |
| author_facet | Liu, Zheng Lin, Honglin Qin, Chonghan Wang, Xiaoyang Gao, Xin Li, Yu Cai, Mengzhang Zhu, Yun Zhong, Zhanping Pei, Qizhi Pan, Zhuoshi Shang, Xiaoran Cui, Bin He, Conghui Zhang, Wentao Wu, Lijun |
| contents | Chart reasoning is a critical capability for Vision Language Models (VLMs). However, the development of open-source models is severely hindered by the lack of high-quality training data. Existing datasets suffer from a dual challenge: synthetic charts are often simplistic and repetitive, while the associated QA pairs are prone to hallucinations and lack the reasoning depth required for complex tasks. To bridge this gap, we propose ChartVerse, a scalable framework designed to synthesize complex charts and reliable reasoning data from scratch. (1) To address the bottleneck of simple patterns, we first introduce Rollout Posterior Entropy (RPE), a novel metric that quantifies chart complexity. Guided by RPE, we develop complexity-aware chart coder to autonomously synthesize diverse, high-complexity charts via executable programs. (2) To guarantee reasoning rigor, we develop truth-anchored inverse QA synthesis. Diverging from standard generation, we adopt an answer-first paradigm: we extract deterministic answers directly from the source code, generate questions conditional on these anchors, and enforce strict consistency verification. To further elevate difficulty and reasoning depth, we filter samples based on model fail-rate and distill high-quality Chain-of-Thought (CoT) reasoning. We curate ChartVerse-SFT-600K and ChartVerse-RL-40K using Qwen3-VL-30B-A3B-Thinking as the teacher. Experimental results demonstrate that ChartVerse-8B achieves state-of-the-art performance, notably surpassing its teacher and rivaling the stronger Qwen3-VL-32B-Thinking. We release our code, model weights, and datasets in https://chartverse.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13606 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch Liu, Zheng Lin, Honglin Qin, Chonghan Wang, Xiaoyang Gao, Xin Li, Yu Cai, Mengzhang Zhu, Yun Zhong, Zhanping Pei, Qizhi Pan, Zhuoshi Shang, Xiaoran Cui, Bin He, Conghui Zhang, Wentao Wu, Lijun Computer Vision and Pattern Recognition Chart reasoning is a critical capability for Vision Language Models (VLMs). However, the development of open-source models is severely hindered by the lack of high-quality training data. Existing datasets suffer from a dual challenge: synthetic charts are often simplistic and repetitive, while the associated QA pairs are prone to hallucinations and lack the reasoning depth required for complex tasks. To bridge this gap, we propose ChartVerse, a scalable framework designed to synthesize complex charts and reliable reasoning data from scratch. (1) To address the bottleneck of simple patterns, we first introduce Rollout Posterior Entropy (RPE), a novel metric that quantifies chart complexity. Guided by RPE, we develop complexity-aware chart coder to autonomously synthesize diverse, high-complexity charts via executable programs. (2) To guarantee reasoning rigor, we develop truth-anchored inverse QA synthesis. Diverging from standard generation, we adopt an answer-first paradigm: we extract deterministic answers directly from the source code, generate questions conditional on these anchors, and enforce strict consistency verification. To further elevate difficulty and reasoning depth, we filter samples based on model fail-rate and distill high-quality Chain-of-Thought (CoT) reasoning. We curate ChartVerse-SFT-600K and ChartVerse-RL-40K using Qwen3-VL-30B-A3B-Thinking as the teacher. Experimental results demonstrate that ChartVerse-8B achieves state-of-the-art performance, notably surpassing its teacher and rivaling the stronger Qwen3-VL-32B-Thinking. We release our code, model weights, and datasets in https://chartverse.github.io. |
| title | ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.13606 |