METAL: Towards Multilingual Meta-Evaluation

arXiv:2404.01667v1 Announce Type: new
Abstract: With the rising human-like precision of Large Language Models (LLMs) in numerous tasks, their utilization in a variety of real-world applications is becoming more prevalent. Several studies have shown that LLMs excel on many standard NLP benchmarks. However, it is challenging to evaluate LLMs due to test dataset contamination and the limitations of traditional metrics. Since human evaluations are difficult to collect, there is a growing interest in the community to use LLMs themselves as …

abstract applications arxiv benchmarks cs.cl dataset evaluation excel however human human-like language language models large language large language models llms meta metal multilingual nlp precision standard studies tasks test type world