paper-with-me

Papers

ChartAB: A Benchmark for Chart Grounding & Dense Alignment

2025-10-30 · Aniruddh Bansal, Davit Soselia, Dang Nguyen, Tianyi Zhou arxiv

Charts play an important role in visualization, reasoning, data analysis, and the exchange of ideas among humans. However, existing vision-language models (VLMs) still lack accurate perception of details and struggle to extract fine-grained structures from charts. Such limitations in chart grounding also hinder their ability to compare multiple charts and reason over them. In this paper, we introduce a novel "ChartAlign Benchmark (ChartAB)" to provide a comprehensive evaluation of VLMs in chart grounding tasks, i.e., extracting tabular data, localizing visualization elements, and recognizing various attributes from charts of diverse types and complexities. We design a JSON template to facilitate the calculation of evaluation metrics specifically tailored for each grounding task. By incorporating a novel two-stage inference workflow, the benchmark can further evaluate VLMs capability to align and compare elements/attributes across two charts. Our analysis of evaluations on several recent VLMs reveals new insights into their perception biases, weaknesses, robustness, and hallucinations in chart understanding. These findings highlight the fine-grained discrepancies among VLMs in chart understanding tasks and point to specific skills that need to be strengthened in current models.

📄 PDF Abstract BibTeX arXiv:2510.26781

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ChartAnchor: Chart Grounding with Structural-Semantic Fidelity

2025-11-30 · Xinhang Li, Jingbo Zhou, Pengfei Luo, Yixiong Xiao 외 arxiv

Recent advances in multimodal large language models (MLLMs) highlight the need for benchmarks that rigorously evaluate structured chart comprehension. Chart grounding refers to the bidirectional alignment between a chart…

Code Generation

ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring

2026-05-08 · Tianhao Niu, Ziyu Han, Xuan Dong, Qingfu Zhu 외 arxiv

Referring expression grounding is a core problem in visual grounding and is widely used as a diagnostic of spatial grounding and reasoning in vision and language models, yet most prior work focuses on natural images. In …

Instance SegmentationReferring ExpressionVisual Grounding

RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning

2025-03-29 · Alexander Vogel, Omar Moured, Yufan Chen, Jiaming Zhang 외

Recently, Vision Language Models (VLMs) have increasingly emphasized document visual grounding to achieve better human-computer interaction, accessibility, and detailed understanding. However, its application to visualiz…

Chart Question AnsweringChart UnderstandingQuestion AnsweringVisual Grounding

VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought

2026-03-12 · Eunsoo Lee, Jeongwoo Lee, Minki Hong, Jangho Choi 외 arxiv

Large vision-language models (LVLMs) struggle to reliably detect visual primitives in charts and align them with semantic representations, which severely limits their performance on complex visual reasoning. This lack of…

Visual Question AnsweringVisual GroundingVisual Reasoning

ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning

2025-11-29 · Zhengzhuo Xu, SiNan Du, Yiyan Qi, SiwenLu 외 arxiv

Multimodal Large Language Models (MLLMs) have emerged as powerful tools for chart comprehension. However, they heavily rely on extracted content via OCR, which leads to numerical hallucinations when chart textual annotat…

Visual Grounding