Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching

TL;DR

Self-Tuning is a novel framework that enhances large language models' ability to acquire, understand, and reflect on new knowledge from raw documents through self-teaching, inspired by the Feynman Technique.

Contribution

It introduces a self-teaching strategy with knowledge-intensive tasks and new datasets to improve LLMs' knowledge acquisition and retention capabilities.

Findings

Self-Tuning outperforms baseline models in knowledge acquisition tasks.

It effectively preserves previous knowledge while learning new information.

Experimental results on Llama2-7B demonstrate consistent improvements.

Abstract

Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve continued pre-training on new documents. However, they frequently face difficulties in extracting stored knowledge. Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM's ability to effectively acquire new knowledge from unseen raw documents through self-teaching. Specifically, we develop a Self-Teaching strategy that augments the documents with a set of knowledge-intensive tasks created in a self-supervised manner, focusing on three crucial aspects: memorization, comprehension, and self-reflection. Additionally, we introduce three Wiki-Newpages-2023-QA datasets to facilitate an in-depth analysis of an LLM's knowledge acquisition ability concerning memorization, extraction, and reasoning. Extensive experimental results on various models, e.g., Llama2-7B reveal that Self-Tuning consistently exhibits superior performance across all knowledge acquisition tasks and excels in preserving previous knowledge.