Evaluating the Generation Capabilities of Large Chinese Language Models

TL;DR

This paper introduces CG-Eval, an automated framework for assessing large Chinese language models across multiple academic domains, featuring the novel Gscore metric for comprehensive performance evaluation.

Contribution

It presents the first automated, multi-domain evaluation framework for Chinese language models and introduces Gscore, a new composite index for nuanced performance measurement.

Findings

Demonstrates the effectiveness of CG-Eval across six key domains.

Provides a comparative analysis of different Chinese language models.

Offers accessible detailed test data and results online.

Abstract

This paper unveils CG-Eval, the first-ever comprehensive and automated evaluation framework designed for assessing the generative capabilities of large Chinese language models across a spectrum of academic disciplines. CG-Eval stands out for its automated process, which critically assesses models based on their proficiency in generating precise and contextually relevant responses to a diverse array of questions within six key domains: Science and Engineering, Humanities and Social Sciences, Mathematical Calculations, Medical Practitioner Qualification Examination, Judicial Examination, and Certified Public Accountant Examination. Alongside this, we introduce Gscore, an innovative composite index developed from a weighted sum of multiple metrics. Gscore uniquely automates the quality measurement of a model's text generation against reference standards, providing a detailed and nuanced assessment of model performance. This automation not only enhances the efficiency and scalability of the evaluation process but also ensures objective and consistent assessment across various models. The detailed test data and results, highlighting the robust capabilities and comparative performance of the evaluated models, are accessible at http://cgeval.besteasy.com/.