MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation
This provides a standardized tool for researchers and developers to evaluate LLMs in multilingual scenarios, though it is incremental as it extends existing evaluation frameworks to new contexts.
The authors tackled the lack of evaluation methods for instruction-following in multilingual and cross-lingual contexts by introducing MaXIFE, a benchmark with 23 languages and 1667 tasks, and applied it to commercial LLMs to establish baseline results.
With the rapid adoption of large language models (LLMs) in natural language processing, the ability to follow instructions has emerged as a key metric for evaluating their practical utility. However, existing evaluation methods often focus on single-language scenarios, overlooking the challenges and differences present in multilingual and cross-lingual contexts. To address this gap, we introduce MaXIFE: a comprehensive evaluation benchmark designed to assess instruction-following capabilities across 23 different languages with 1667 verifiable instruction tasks. MaXIFE integrates both Rule-Based Evaluation and Model-Based Evaluation, ensuring a balance of efficiency and accuracy. We applied MaXIFE to evaluate several leading commercial LLMs, establishing baseline results for future comparisons. By providing a standardized tool for multilingual instruction-following evaluation, MaXIFE aims to advance research and development in natural language processing.