FilBench: Can LLMs Understand and Generate Filipino?

TL;DR

FilBench is a new benchmark designed to evaluate the capabilities of large language models in understanding and generating Filipino, revealing current limitations and highlighting the need for language-specific NLP development.

Contribution

This work introduces FilBench, the first comprehensive Filipino-centric benchmark for evaluating LLMs across diverse NLP tasks in Filipino, Tagalog, and Cebuano.

Findings

GPT-4o scores 72.23% on FilBench

Models trained for Southeast Asian languages underperform

FilBench is challenging for current state-of-the-art LLMs

Abstract

Despite the impressive performance of LLMs on English-based tasks, little is known about their capabilities in specific languages such as Filipino. In this work, we address this gap by introducing FilBench, a Filipino-centric benchmark designed to evaluate LLMs across a diverse set of tasks and capabilities in Filipino, Tagalog, and Cebuano. We carefully curate the tasks in FilBench to reflect the priorities and trends of NLP research in the Philippines such as Cultural Knowledge, Classical NLP, Reading Comprehension, and Generation. By evaluating 27 state-of-the-art LLMs on FilBench, we find that several LLMs suffer from reading comprehension and translation capabilities. Our results indicate that FilBench is challenging, with the best model, GPT-4o, achieving only a score of 72.23%. Moreover, we also find that models trained specifically for Southeast Asian languages tend to underperform on FilBench, with the highest-performing model, SEA-LION v3 70B, achieving only a score of 61.07%. Our work demonstrates the value of curating language-specific LLM benchmarks to aid in driving progress on Filipino NLP and increasing the inclusion of Philippine languages in LLM development.