Despite Southeast Asia’s (SEA) extraordinary linguistic and cultural diversity, the region remains significantly underrepresented in vision-language (VL) research, resulting in AI models that inadequately capture SEA cultural nuances. To fill this gap, we present SEA-VL, an open-source initiative dedicated to developing culturally relevant high-quality datasets for SEA languages. By involving contributors from SEA countries, SEA-VL ensures better cultural relevance and diversity, fostering greater inclusivity of underrepresented languages and cultural depictions in VL research. Our methodology employed three approaches: community-driven crowdsourcing with SEA contributors, automated image crawling, and synthetic image generation. We evaluated each method’s effectiveness in capturing cultural relevance. We found that image crawling achieves approximately ~85% cultural relevance while being more cost- and time-efficient than crowdsourcing, whereas synthetic image generation failed to accurately reflect SEA cultural nuances and contexts. Collectively, we gathered 1.28 million SEA culturally relevant images, more than 50 times larger than other existing datasets. This work bridges the representation gap in SEA, establishes a foundation for developing culturally aware AI systems for this region, and provides a replicable framework for addressing representation gaps in other underrepresented regions.

This study explores the ethical challenges faced by Indonesian Large Language Models (LLMs), particularly focusing on their ability to distinguish between ethical and unethical instructions. As LLMs become increasingly integrated into sensitive applications, ensuring their ethical operation is crucial. A key contribution of this study is the introduction of the Anak Baik dataset, a resource designed to enhance the ethical reasoning capabilities of Indonesian LLMs. The phrase “Anak Baik”, meaning “Good Boy”, symbolizes the ideal of ethical behavior, as a well-behaved child refrains from engaging in harmful actions. The dataset comprises instruction-response pairs in Indonesian, crafted for Supervised Fine-Tuning (SFT) tasks. It includes examples of both ethical and unethical responses to guide models in learning to generate responses that uphold moral standards. Leveraging Low-Rank Adaptation (LoRA) on models such as Komodo and Cendol shows a significant improvement in ethical decision-making processes. This enhanced performance is quantitatively validated through substantial increases in BLEU and ROUGE scores, indicating a stronger alignment with socially responsible behavior.

This paper presents the participation of DBMS-KU Interpolation system in WMT19 shared task, namely, Kazakh-English language pair. We examine the use of interpolation method using a different language model order. Our Interpolation system combines a direct translation with Russian as a pivot language. We use 3-gram and 5-gram language model orders to perform the language translation in this work. To reduce noise in the pivot translation process, we prune the phrase table of source-pivot and pivot-target. Our experimental results show that our Interpolation system outperforms the Baseline in terms of BLEU-cased score by +0.5 and +0.1 points in Kazakh-English and English-Kazakh, respectively. In particular, using the 5-gram language model order in our system could obtain better BLEU-cased score than utilizing the 3-gram one. Interestingly, we found that by employing the Interpolation system could reduce the perplexity score of English-Kazakh when using 3-gram language model order.