Metraipolis › archive › dc_06b36d425fc9

VizDAGuide: Misleading Chart Question Answering in Compact Vision Language Models via DAG-Structured Supervision — arXiv:2611.03023

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03023
License (as archived)
CC0-1.0
Archived
2026-11-03T18:35:03.893Z
SHA-256 of the archived text
df8c88e567ecc72d711c46e6391803b9eb4f6a6411b9382352a3fe4f3ef96bac
Stable URL of this page
https://metraipolis.com/documento/dc_06b36d425fc9

How to cite

VizDAGuide: Misleading Chart Question Answering in Compact Vision Language Models via DAG-Structured Supervision — arXiv:2611.03023 — arXiv (en), https://arxiv.org/abs/2611.03023 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06b36d425fc9 (Metraipolis archive dc_06b36d425fc9, sha256 df8c88e567ecc72d711c46e6391803b9eb4f6a6411b9382352a3fe4f3ef96bac)
BibTeX
@misc{dc06b36d425fc9,
  title = {VizDAGuide: Misleading Chart Question Answering in Compact Vision Language Models via DAG-Structured Supervision — arXiv:2611.03023},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03023},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06b36d425fc9; sha256 df8c88e567ecc72d711c46e6391803b9eb4f6a6411b9382352a3fe4f3ef96bac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03023. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Misleading charts can lead vision-language models to conclusions that conflict with underlying data. Existing work focuses on inference-time strategies, while training-time supervision remains less explored. We present VizDAGuide, a DAG-structured supervision method for misleading-chart question answering. The method represents intermediate reasoning states and their dependencies as a directed acyclic graph, assigns supervision weights according to their roles, and serializes the graph into a unified training target for open-ended and multiple-choice QA with single-pass inference. Experiments on two benchmarks across Qwen3-VL and InternVL3.5 models show improvements over a content- and weight-matched Linear CoT-SFT baseline on both answer formats. Process-level evaluation shows gains in grounding and operation execution, while ablations indicate that dependency structure and weighted supervision are most effective when combined. These results support DAG-structured weighted supervision for misleading-chart question answering.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2611.03023 — 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 2026-11-03T18:12:37.998Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).