SEA-HELM: Southeast Asian Holistic Evaluation of Language Models
This work addresses the problem of inadequate multilingual and multicultural evaluation tools for LLMs in Southeast Asia, which is incremental as it builds on existing benchmarks by adding cultural and linguistic specificity.
The authors tackled the lack of comprehensive and culturally representative benchmarks for evaluating Large Language Models (LLMs) in Southeast Asian languages by introducing SEA-HELM, a holistic evaluation suite covering five core pillars, including NLP classics, LLM-specifics, linguistics, culture, and safety, for languages such as Filipino, Indonesian, Tamil, Thai, and Vietnamese, and they made the code publicly available.
With the rapid emergence of novel capabilities in Large Language Models (LLMs), the need for rigorous multilingual and multicultural benchmarks that are integrated has become more pronounced. Though existing LLM benchmarks are capable of evaluating specific capabilities of LLMs in English as well as in various mid- to low-resource languages, including those in the Southeast Asian (SEA) region, a comprehensive and culturally representative evaluation suite for the SEA languages has not been developed thus far. Here, we present SEA-HELM, a holistic linguistic and cultural LLM evaluation suite that emphasises SEA languages, comprising five core pillars: (1) NLP Classics, (2) LLM-specifics, (3) SEA Linguistics, (4) SEA Culture, (5) Safety. SEA-HELM currently supports Filipino, Indonesian, Tamil, Thai, and Vietnamese. We also introduce the SEA-HELM leaderboard, which allows users to understand models' multilingual and multicultural performance in a systematic and user-friendly manner. We make the SEA-HELM evaluation code publicly available.