ChartWalker: Benchmarking the Cross-Chart RAG Task

Hugging Face Daily Papers Papers

Summary

ChartWalker introduces a novel framework for cross-chart retrieval-augmented generation (RAG) using hierarchical knowledge graph construction and structure-aware sampling. It releases a challenging benchmark (ChartWalker-Bench) and an agentic baseline (ChartWalker-Agent), revealing significant performance gaps in current RAG paradigms.

Cross-Chart Retrieval-Augmented Generation (RAG) is critical for complex multi-modal analytical tasks in scientific, business, and political domains. However, existing benchmarks either focus on tables, which are well-structured and textualized, or generate cross-chart questions by simply extracting key points, which often induces lexical overlap between queries and evidence and yields logically inconsistent reasoning chains. To address this, we introduce ChartWalker, a novel framework for constructing challenging cross-chart RAG tasks. ChartWalker features a hierarchical knowledge graph construction method tailored to charts, which organizes entities and relations by granularity to preserve analytical structure. We then propose a structure-aware sampling algorithm that synthesizes semantically coherent, multi-hop reasoning paths, enabling explicit control over query difficulty and granularity for QA generation. Built with this framework, we release ChartWalker-Bench, a comprehensive benchmark spanning diverse domains and cross-chart query types. Extensive evaluations across major RAG paradigms reveal significant performance gaps, underscoring the benchmark's difficulty and utility. Furthermore, we provide ChartWalker-Agent, an agentic baseline to facilitate analysis and inspire future system design.
Original Article
View Cached Full Text

Cached at: 06/24/26, 01:48 PM

Paper page - ChartWalker: Benchmarking the Cross-Chart RAG Task

Source: https://huggingface.co/papers/2606.23997

Abstract

ChartWalker presents a novel framework for cross-chart retrieval-augmented generation with hierarchical knowledge graph construction and structure-aware sampling for challenging multi-modal analytical tasks.

Cross-Chart Retrieval-Augmented Generation(RAG) is critical for complex multi-modal analytical tasks in scientific, business, and political domains. However, existing benchmarks either focus on tables, which are well-structured and textualized, or generate cross-chart questions by simply extracting key points, which often induces lexical overlap between queries and evidence and yields logically inconsistent reasoning chains. To address this, we introduce ChartWalker, a novel framework for constructing challenging cross-chart RAG tasks. ChartWalker features ahierarchical knowledge graph constructionmethod tailored to charts, which organizes entities and relations by granularity to preserve analytical structure. We then propose astructure-aware samplingalgorithm that synthesizes semantically coherent,multi-hop reasoning paths, enabling explicit control over query difficulty and granularity for QA generation. Built with this framework, we releaseChartWalker-Bench, a comprehensive benchmark spanning diverse domains and cross-chart query types. Extensive evaluations across major RAG paradigms reveal significant performance gaps, underscoring the benchmark’s difficulty and utility. Furthermore, we provideChartWalker-Agent, an agentic baseline to facilitate analysis and inspire future system design.

View arXiv pageView PDFGitHub0Add to collection

Get this paper in your agent:

hf papers read 2606\.23997

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.23997 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.23997 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.23997 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats

Hugging Face Daily Papers

ChartArena is a comprehensive bilingual benchmark for chart parsing that evaluates models across eight chart families and three visual scenarios (digital, printed, hand-drawn), using a human-agent annotation pipeline and format-agnostic evaluation. Evaluations of 26 MLLMs reveal that while proprietary models lead overall, open-source models are catching up, and diagrammatic structures and hand-drawn scenarios remain challenging.