@inproceedings{bao-etal-2026-learning,
    title = "Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding",
    author = "Bao, Jianzhu  and
      Zhang, Haozhen  and
      Dong, Kuicai  and
      Wu, Bozhi  and
      Modi, Sarthak Ketanbhai  and
      Lim, Zi Pong  and
      Teo, Yon Shin  and
      Wang, Wenya",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1280/",
    pages = "27775--27797",
    ISBN = "979-8-89176-390-6",
    abstract = "Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasingly large synthetic datasets.However, scaling SFT data alone is inefficient and overlooks a key property of charts: charts are programmatically generated visual artifacts, where small, code-controlled visual changes can induce drastic shifts in semantics and correct answers.Learning this counterfactual sensitivity requires VLMs to discriminate fine-grained visual differences, yet standard SFT treats training instances independently and provides limited supervision to enforce this behavior.To address this, we introduce ChartCF, a data-efficient training framework designed to enhance counterfactual sensitivity.ChartCF consists of: (1) a counterfactual data synthesis pipeline via code modification, (2) a chart similarity-based data selection strategy that filters overly difficult samples for improved training efficiency, and (3) multimodal preference optimization across both textual and visual modalities.Experiments on five benchmarks show that ChartCF achieves superior or comparable performance to strong chart-specific VLMs while using significantly less training data."
}