{"ID":2865088,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21946","arxiv_id":"2509.21946","title":"Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration","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 - marked by indirect language, polarized figures, and entangled sentiment and stance - LLMs often display systematic biases such as sentiment leakage and favoritism toward entities. These biases undermine fairness and reliability. We present ThaiFACTUAL, a lightweight, model-agnostic calibration framework that mitigates political bias without requiring fine-tuning. ThaiFACTUAL uses counterfactual data augmentation and rationale-based supervision to disentangle sentiment from stance and reduce bias. We also release the first high-quality Thai political stance dataset, annotated with stance, sentiment, rationales, and bias markers across diverse entities and events. Experimental results show that ThaiFACTUAL significantly reduces spurious correlations, enhances zero-shot generalization, and improves fairness across multiple LLMs. This work highlights the importance of culturally grounded debiasing techniques for underrepresented languages.","short_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 - marked by indirect language, polarized figures, and entangled sentiment and stance - LLMs often display systematic biases such as sentiment leakage an...","url_abs":"https://arxiv.org/abs/2509.21946","url_pdf":"https://arxiv.org/pdf/2509.21946v1","authors":"[\"Kasidit Sermsri\",\"Teerapong Panboonyuen\"]","published":"2025-09-26T06:26:21Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}