LKValues: Aligning Large Language Models with Sri Lankan Societal Values
2026-07-22 • Computation and Language
Computation and Language
AI summaryⓘ
The authors focus on making large language models (LLMs) better understand and respect Sri Lankan cultural values, which are often overlooked because most models are trained with Western ideas. They created a new dataset called LKValues by surveying people in Sri Lanka and combining global and local values, then made training and testing materials in Sinhala and English. After testing and fine-tuning several models, they found that newer, bigger models still struggle with local value understanding, but their approach helps improve this issue, especially for the Qwen models. This work provides a useful method and dataset for making AI more culturally aware in low-resource settings like Sri Lanka.
Value alignmentLarge language modelsCultural biasSri LankaSinhalaMultilingual societiesFine-tuningBenchmark datasetCross-lingual evaluationLow-resource NLP
Authors
Nethmi Muthugala, Supryadi, Surangika Ranathunga, Nisansa de Silva, Ruijie Tao, Ovindu Gunatunga, Pengyun Zhu, Shaowei Zhang, Jingting Zheng, Deyi Xiong
Abstract
Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local values in multilingual societies such as Sri Lanka that have their unique cultural dynamics. Existing benchmarks overlook Sri Lankan-contextualized values in its official language Sinhala, hindering culturally sensitive evaluation and fine-tuning. To bridge this gap, we propose LKValues, the first survey-grounded resource suite for Sri Lankan value alignment. From a trilingual survey of 205 respondents, blending adapted global frameworks and LLM-elicited local constructs, we derive 40 majority-endorsed societal values. Using these values, we construct LKvaluesIT, a Sinhala-English news-derived instruction corpus containing 150k scenario-based instances, and LKvaluesBench, a value-sensitive evaluation benchmark of 1,000 instances. We evaluate a set of proprietary and open-weight LLMs with LKvaluesBench. We fine-tune three open-weight base models (Qwen3.5-4B-Base, Qwen3.5-9B-Base, and Aya-Expanse-8B-Base). Our experiments show that newer and larger LLMs still exhibit low-resource and cultural value-alignment gaps. LKValues fine-tuning improves Qwen-family models in English and Sinhala, reducing invalid outputs and cross-lingual disparities, though gains remain model-family dependent. These highlight LKValues efficacy in embedding Sri Lankan values, offering a replicable pipeline for low-resource, country-specific pluralist value alignment. The dataset is publicly available at https://github.com/NextME14/LKValues.