SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection

TL;DR

SelectIT introduces an uncertainty-aware self-reflection method that enables efficient instruction data selection for LLMs, improving performance without additional models or data, and demonstrates its effectiveness across models and domains.

Contribution

It proposes a novel LLM-based data selection approach for instruction tuning, creating the Selective Alpaca dataset and showing improved model performance without extra resource requirements.

Findings

Selective Alpaca enhances model abilities.

SelectIT improves robustness across models.

Longer, high-quality data boosts instruction tuning.

Abstract

Instruction tuning (IT) is crucial to tailoring large language models (LLMs) towards human-centric interactions. Recent advancements have shown that the careful selection of a small, high-quality subset of IT data can significantly enhance the performance of LLMs. Despite this, common approaches often rely on additional models or data, which increases costs and limits widespread adoption. In this work, we propose a novel approach, termed SelectIT, that capitalizes on the foundational capabilities of the LLM itself. Specifically, we exploit the intrinsic uncertainty present in LLMs to more effectively select high-quality IT data, without the need for extra resources. Furthermore, we introduce a curated IT dataset, the Selective Alpaca, created by applying SelectIT to the Alpaca-GPT4 dataset. Empirical results demonstrate that IT using Selective Alpaca leads to substantial model ability enhancement. The robustness of SelectIT has also been corroborated in various foundation models and domain-specific tasks. Our findings suggest that longer and more computationally intensive IT data may serve as superior sources of IT, offering valuable insights for future research in this area. Data, code, and scripts are freely available at https://github.com/Blue-Raincoat/SelectIT.