IndoPref: A Multi-Domain Pairwise Preference Dataset for Indonesian

Abstract: Over 200 million people speak Indonesian, yet the language remains significantly underrepresented in preference-based research for LLMs. Most existing multilingual datasets are derived from English translations, often resulting in content that lacks cultural and linguistic authenticity. To address this gap, we introduce IndoPref, the first fully human-authored and multi-domain Indonesian preference dataset specifically designed to evaluate the naturalness and quality of LLM-generated text. All annotations are natively written in Indonesian and evaluated using Krippendorff's alpha, demonstrating strong inter-annotator agreement. Additionally, we benchmark the dataset across multiple LLMs and assess the output quality of each model.