FarsEval-PKBETS: A new diverse benchmark for evaluating Persian large language models
This addresses the problem of limited evaluation resources for Persian LLMs, providing a culturally relevant benchmark for researchers and developers in natural language processing.
The paper tackles the lack of evaluation benchmarks for Persian large language models by introducing FarsEval-PKBETS, a diverse benchmark with 4000 questions across multiple domains, and finds that current models like Llama3-70B achieve below 50% accuracy on it.
Research on evaluating and analyzing large language models (LLMs) has been extensive for resource-rich languages such as English, yet their performance in languages such as Persian has received considerably less attention. This paper introduces FarsEval-PKBETS benchmark, a subset of FarsEval project for evaluating large language models in Persian. This benchmark consists of 4000 questions and answers in various formats, including multiple choice, short answer and descriptive responses. It covers a wide range of domains and tasks,including medicine, law, religion, Persian language, encyclopedic knowledge, human preferences, social knowledge, ethics and bias, text generation, and respecting others' rights. This bechmark incorporates linguistics, cultural, and local considerations relevant to the Persian language and Iran. To ensure the questions are challenging for current LLMs, three models -- Llama3-70B, PersianMind, and Dorna -- were evaluated using this benchmark. Their average accuracy was below 50%, meaning they provided fully correct answers to fewer than half of the questions. These results indicate that current language models are still far from being able to solve this benchmark