Metraipolis › archive › dc_ccffba2de880

DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation? — arXiv:2608.26757

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.26757
License (as archived): CC0-1.0
Archived: 2026-10-17T14:22:59.860Z
SHA-256 of the archived text: b5032cf66e416e4d782473237321d3bc44806bf9fc4ebe8441c174c2e493adeb
Stable URL of this page: https://metraipolis.com/documento/dc_ccffba2de880

How to cite

DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation? — arXiv:2608.26757 — arXiv (en), https://arxiv.org/abs/2608.26757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccffba2de880 (Metraipolis archive dc_ccffba2de880, sha256 b5032cf66e416e4d782473237321d3bc44806bf9fc4ebe8441c174c2e493adeb)

BibTeX

@misc{dcccffba2de880,
  title = {DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation? — arXiv:2608.26757},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26757},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccffba2de880; sha256 b5032cf66e416e4d782473237321d3bc44806bf9fc4ebe8441c174c2e493adeb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Faithful chart generation in real-world data-science workflows requires grounding visualizations in scattered evidence, computing chart-ready quantities, and rendering them accurately. Modern LLMs can produce visually plausible, instruction-compliant charts, yet data-level hallucinations remain difficult to detect in long, noisy, and multimodal contexts. To measure this gap, we introduce DEEPCHART, an expert-annotated benchmark of 1,482 task-conditioned chart-generation instances drawn from real-world scientific papers, financial filings, and ecosystem reports. DEEPCHART formulates chart generation as an Extract--Reason--Visualize pipeline and evaluates source-data extraction, derived-data reasoning, and chart rendering stage by stage. Experiments with state-of-the-art models show that visually plausible charts often conceal data-level hallucinations, with extraction and reasoning errors common in realistic long and multimodal settings. These findings suggest that larger context windows alone are insufficient; faithful chart generation also requires reliable evidence extraction and quantitative reasoning before rendering. Our benchmark and associated resources are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26757 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T13:16:53.518Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).