大型语言模型的自动指令演化
Automatic Instruction Evolving for Large Language Models
AI总结：
本文提出 Auto Evol-Instruct 端到端框架，利用大型语言模型自动分析指令数据并迭代优化演化策略，无需人工干预，在 MT-Bench 等多个基准上超越人类设计方法。
摘要：
使用 Evol-Instruct 微调大型预训练语言模型在广泛任务上取得了令人鼓舞的结果。然而，为指令演化设计有效的演化方法需要大量人类专业知识。本文提出 Auto Evol-Instruct，这是一个使用大型语言模型演化指令数据集且无需任何人工努力的端到端框架。该框架自动分析并总结适合给定指令数据的演化策略，并根据指令演化过程中暴露出的问题迭代改进演化方法。我们的大量实验表明，由 Auto Evol-Instruct 优化的最佳方法在包括 MT-Bench、AlpacaEval、GSM8K 和 HumanEval 在内的各种基准上优于人类设计的方法。
英文摘要：
Fine-tuning large pre-trained language models with Evol-Instruct has achieved encouraging results across a wide range of tasks. However, designing effective evolving methods for instruction evolution requires substantial human expertise. This paper proposes Auto Evol-Instruct, an end-to-end framework that evolves instruction datasets using large language models without any human effort. The framework automatically analyzes and summarizes suitable evolutionary strategies for the given instruction data and iteratively improves the evolving method based on issues exposed during the instruction evolution process. Our extensive experiments demonstrate that the best method optimized by Auto Evol-Instruct outperforms human-designed methods on various benchmarks, including MT-Bench, AlpacaEval, GSM8K, and HumanEval.
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。
