Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sermsri, Kasidit, Panboonyuen, Teerapong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909808634888192
author Sermsri, Kasidit
Panboonyuen, Teerapong
author_facet Sermsri, Kasidit
Panboonyuen, Teerapong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21946
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration
Sermsri, Kasidit
Panboonyuen, Teerapong
Computation and Language
Artificial Intelligence
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.
title Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.21946