Automatic Instruction Evolving for Large Language Models

TL;DR

Auto Evol-Instruct is an automated framework that evolves instruction datasets for large language models, outperforming human-designed methods without requiring human expertise.

Contribution

It introduces an end-to-end automated approach for evolving instruction datasets using large language models, reducing reliance on human-designed strategies.

Findings

Outperforms human-designed methods on multiple benchmarks

Automatically analyzes and summarizes evolutionary strategies

Iteratively improves instruction evolution process

Abstract

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.