@inproceedings{mahbub-etal-2025-charts,
    title = "From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text",
    author = "Mahbub, Ridwan  and
      Islam, Mohammed Saidul  and
      Nayeem, Mir Tafseer  and
      Laskar, Md Tahmid Rahman  and
      Rahman, Mizanur  and
      Joty, Shafiq  and
      Hoque, Enamul",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1472/",
    pages = "28917--28935",
    ISBN = "979-8-89176-332-6",
    abstract = "Charts are very common for exploring dataand communicating insights, but extracting key takeaways from charts and articulating them in natural language can be challenging. The chart-to-text task aims to automate this process by generating textual summaries of charts. While with the rapid advancement of large Vision-Language Models (VLMs), we have witnessed great progress in this domain, little to no attention has been given to potential biases in their outputs. This paper investigates how VLMs can amplify geo-economic biases when generating chart summaries, potentially causing societal harm. Specifically, we conduct a large-scale evaluation of geo-economic biases in VLM-generated chart summaries across 6,000 chart-country pairs from six widely used proprietary and open-source models to understand how a country{'}s economic status influences the sentiment of generated summaries. Our analysis reveals that existing VLMs tend to produce more positive descriptions for high-income countries compared to middle- or low-income countries, even when country attribution is the only variable changed. We also find that models such as GPT-4o-mini, Gemini-1.5-Flash, and Phi-3.5 exhibit varying degrees of bias. We further explore inference-time prompt-based debiasing techniques using positive distractors but find them only partially effective, underscoring the complexity of the issue and the need for more robust debiasing strategies. Our code and dataset are available at {\ensuremath{<}}$redacted${\ensuremath{>}}."
}