F\`ux\`i: A Benchmark for Evaluating Language Models on Ancient Chinese Text Understanding and Generation

TL;DR

F ext`ux ext`i is a comprehensive benchmark designed to evaluate large language models on both understanding and generating ancient Chinese texts, addressing a critical gap in cultural and linguistic assessment.

Contribution

It introduces a balanced, multi-task benchmark with novel evaluation metrics and a systematic framework for assessing ancient Chinese language models.

Findings

Models perform well in comprehension but poorly in generation tasks.

Generation tasks requiring cultural knowledge are particularly challenging.

The benchmark reveals significant gaps in current LLM capabilities for ancient Chinese.

Abstract

Ancient Chinese text processing presents unique challenges for large language models (LLMs) due to its distinct linguistic features, complex structural constraints, and rich cultural context. While existing benchmarks have primarily focused on evaluating comprehension through multiple-choice questions, there remains a critical gap in assessing models' generative capabilities in classical Chinese. We introduce F\`ux\`i, a comprehensive benchmark that evaluates both understanding and generation capabilities across 21 diverse tasks. Our benchmark distinguishes itself through three key contributions: (1) balanced coverage of both comprehension and generation tasks, including novel tasks like poetry composition and couplet completion, (2) specialized evaluation metrics designed specifically for classical Chinese text generation, combining rule-based verification with fine-tuned LLM evaluators, and (3) a systematic assessment framework that considers both linguistic accuracy and cultural authenticity. Through extensive evaluation of state-of-the-art LLMs, we reveal significant performance gaps between understanding and generation tasks, with models achieving promising results in comprehension but struggling considerably in generation tasks, particularly those requiring deep cultural knowledge and adherence to classical formats. Our findings highlight the current limitations in ancient Chinese text processing and provide insights for future model development. The benchmark, evaluation toolkit, and baseline results are publicly available to facilitate research in this domain.