@inproceedings{sermsri-panboonyuen-2025-debiasing,
    title = "Debiasing Large Language Models in {T}hai Political Stance Detection via Counterfactual Calibration",
    author = "Sermsri, Kasidit  and
      Panboonyuen, Teerapong",
    editor = "Zhang, Chen  and
      Allaway, Emily  and
      Shen, Hua  and
      Miculicich, Lesly  and
      Li, Yinqiao  and
      M'hamdi, Meryem  and
      Limkonchotiwat, Peerat  and
      Bai, Richard He  and
      T.y.s.s., Santosh  and
      Han, Sophia Simeng  and
      Thapa, Surendrabikram  and
      Rim, Wiem Ben",
    booktitle = "Proceedings of the 9th Widening NLP Workshop",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.winlp-main.13/",
    pages = "56--64",
    ISBN = "979-8-89176-351-7",
    abstract = "Political stance detection in low-resource and culturally complex settings poses a critical challenge for large language models (LLMs). In the Thai political landscape{---}rich with indirect expressions, polarized figures, and sentiment-stance entanglement{---}LLMs often exhibit systematic biases, including sentiment leakage and entity favoritism. These biases not only compromise model fairness but also degrade predictive reliability in real-world applications. We introduce ThaiFACTUAL, a lightweight, model-agnostic calibration framework that mitigates political bias without fine-tuning LLMs. ThaiFACTUAL combines counterfactual data augmentation with rationale-based supervision to disentangle sentiment from stance and neutralize political preferences. We curate and release the first high-quality Thai political stance dataset with stance, sentiment, rationale, and bias markers across diverse political entities and events. Our results show that ThaiFACTUAL substantially reduces spurious correlations, improves zero-shot generalization, and enhances fairness across multiple LLMs. This work underscores the need for culturally grounded bias mitigation and offers a scalable blueprint for debiasing LLMs in politically sensitive, underrepresented languages."
}