M-IFEval：多语言指令遵循评估
M-IFEval: Multilingual Instruction-Following Evaluation
AI总结：
本文提出多语言指令遵循评估基准M-IFEval，将IFEval扩展至法、日、西三种语言并涵盖通用与语言特定指令，在8个主流LLM上验证了多语言评估的必要性。
摘要：
指令遵循是现代大语言模型（LLMs）的核心能力，因此评估这一能力对于理解这些模型至关重要。文献中的指令遵循评估（IFEval）基准使用客观标准来实现这一目标，无需主观的AI或人类判断即可衡量LLM性能。然而，它仅包含英语指令，限制了其评估其他语言LLM的能力。我们提出了多语言指令遵循评估（M-IFEval）基准，将评估扩展到法语、日语和西班牙语，包含通用指令和语言特定指令。将该基准应用于8个最先进的LLM，我们发现不同语言和指令类型上的基准性能差异可能很大，这凸显了多语言基准在多元文化背景下评估LLM的重要性。
英文摘要：
Instruction following is a core capability of modern Large language models (LLMs), making evaluating this capability essential to understanding these models. The Instruction Following Evaluation (IFEval) benchmark from the literature does this using objective criteria, offering a measure of LLM performance without subjective AI or human judgement. However, it only includes English instructions, limiting its ability to assess LLMs in other languages. We propose the Multilingual Instruction Following Evaluation (M-IFEval) benchmark, expanding the evaluation to French, Japanese, and Spanish, with both general and language-specific instructions. Applying this benchmark to 8 state-of-the-art LLMs, we find that benchmark performance across languages and instruction types can vary widely, underscoring the importance of a multilingual benchmark for evaluating LLMs in a diverse cultural context.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
