Reflection-Tuning: Recycling Data for Better Instruction-Tuning

Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Tianyi Zhou

Keywords: Natrual Language Process, Large Language Model, Instruction Tuning

TL;DR: This paper proposes a recycling method to improve the quality of instruction tuning dataset.

Abstract: Recent advancements in Large Language Models (LLMs) have expanded the horizons of natural language understanding and generation. Notably, the output control and alignment with the input of LLMs can be refined through instruction tuning. However, as highlighted in several studies, low-quality data in the training set are usually detrimental to instruction tuning, resulting in inconsistent or even misleading LLM outputs. We propose a novel method, termed ``reflection-tuning,'' which addresses the problem by self-improvement and judging capabilities of LLMs. This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data. Extensive experiments on widely used evaluation benchmarks show that LLMs trained with our recycled data outperform those trained with existing datasets in various benchmarks. Codes, data, and models are available at https://github.com/tianyi-lab/Reflection_Tuning.

Submission Number: 99