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.</p>\n","updatedAt":"2026-06-24T11:16:24.022Z","author":{"_id":"642f6c64f945a8a5c9ee5b5d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/642f6c64f945a8a5c9ee5b5d/V_4S_39gZc3ttiO4rXccj.png","fullname":"XiaofengShi","name":"MonteXiaofeng","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":9,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8948475122451782},"editors":["MonteXiaofeng"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/642f6c64f945a8a5c9ee5b5d/V_4S_39gZc3ttiO4rXccj.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.23997","authors":[{"_id":"6a3bbc255ac9fb074498496e","name":"Ning Tang","hidden":false},{"_id":"6a3bbc255ac9fb074498496f","name":"Chenghan Xie","hidden":false},{"_id":"6a3bbc255ac9fb0744984970","name":"Hanyang Yuan","hidden":false},{"_id":"6a3bbc255ac9fb0744984971","name":"Yi Li","hidden":false},{"_id":"6a3bbc255ac9fb0744984972","name":"Renhong Huang","hidden":false},{"_id":"6a3bbc255ac9fb0744984973","name":"Qian Kou","hidden":false},{"_id":"6a3bbc255ac9fb0744984974","name":"Xiaofeng Shi","hidden":false},{"_id":"6a3bbc255ac9fb0744984975","name":"Hua Zhou","hidden":false},{"_id":"6a3bbc255ac9fb0744984976","name":"Jiarong Xu","hidden":false}],"publishedAt":"2026-06-22T00:00:00.000Z","submittedOnDailyAt":"2026-06-24T00:00:00.000Z","title":"ChartWalker: Benchmarking the Cross-Chart RAG Task","submittedOnDailyBy":{"_id":"642f6c64f945a8a5c9ee5b5d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/642f6c64f945a8a5c9ee5b5d/V_4S_39gZc3ttiO4rXccj.png","isPro":false,"fullname":"XiaofengShi","user":"MonteXiaofeng","type":"user","name":"MonteXiaofeng"},"summary":"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.","upvotes":2,"discussionId":"6a3bbc265ac9fb0744984977","githubRepo":"https://github.com/downing777/ChartWalker_Pub","githubRepoAddedBy":"user","ai_summary":"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.","ai_keywords":["cross-chart retrieval-augmented generation","hierarchical knowledge graph construction","structure-aware sampling","multi-hop reasoning paths","ChartWalker-Bench","ChartWalker-Agent"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":0,"organization":{"_id":"61be9739d2f9358e24ca0a4f","name":"BAAI","fullname":"Beijing Academy of Artificial Intelligence","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1664511063789-632c234f42c386ebd2710434.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"642f6c64f945a8a5c9ee5b5d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/642f6c64f945a8a5c9ee5b5d/V_4S_39gZc3ttiO4rXccj.png","isPro":false,"fullname":"XiaofengShi","user":"MonteXiaofeng","type":"user"},{"_id":"63c1699e40a26dd2db32400d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63c1699e40a26dd2db32400d/3N0-Zp8igv8-52mXAdiiq.jpeg","isPro":false,"fullname":"Chroma","user":"Chroma111","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"61be9739d2f9358e24ca0a4f","name":"BAAI","fullname":"Beijing Academy of Artificial Intelligence","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1664511063789-632c234f42c386ebd2710434.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.23997.md","query":{}}">
ChartWalker: Benchmarking the Cross-Chart RAG Task
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 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.
Community
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.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2606.23997 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.23997 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.23997 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.