BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models
This addresses the need for systematic evaluation tools for Burmese, a low-resource language, though it is incremental as it applies existing benchmarking methods to a new language.
The authors tackled the problem of evaluating large language models for Burmese by introducing BURMESE-SAN, the first holistic benchmark covering NLP competencies like understanding, reasoning, and generation, and found that performance depends more on architectural design and regional fine-tuning than on model scale, with newer models showing substantial gains.
We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP competencies: understanding (NLU), reasoning (NLR), and generation (NLG). BURMESE-SAN consolidates seven subtasks spanning these competencies, including Question Answering, Sentiment Analysis, Toxicity Detection, Causal Reasoning, Natural Language Inference, Abstractive Summarization, and Machine Translation, several of which were previously unavailable for Burmese. The benchmark is constructed through a rigorous native-speaker-driven process to ensure linguistic naturalness, fluency, and cultural authenticity while minimizing translation-induced artifacts. We conduct a large-scale evaluation of both open-weight and commercial LLMs to examine challenges in Burmese modeling arising from limited pretraining coverage, rich morphology, and syntactic variation. Our results show that Burmese performance depends more on architectural design, language representation, and instruction tuning than on model scale alone. In particular, Southeast Asia regional fine-tuning and newer model generations yield substantial gains. Finally, we release BURMESE-SAN as a public leaderboard to support systematic evaluation and sustained progress in Burmese and other low-resource languages. https://leaderboard.sea-lion.ai/detailed/MY