Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
This work addresses the fundamental understanding of self-improvement mechanisms in LLMs, which is incremental as it builds on existing empirical successes to provide a controlled study.
The authors tackled the problem of understanding self-improvement in large language models by formalizing the generation-verification gap and discovered that a variant of this gap scales monotonically with model pre-training flops, providing insights into when and how self-improvement works.
Self-improvement is a mechanism in Large Language Model (LLM) pre-training, post-training and test-time inference. We explore a framework where the model verifies its own outputs, filters or reweights data based on this verification, and distills the filtered data. Despite several empirical successes, a fundamental understanding is still lacking. In this work, we initiate a comprehensive, modular and controlled study on LLM self-improvement. We provide a mathematical formulation for self-improvement, which is largely governed by a quantity which we formalize as the generation-verification gap. Through experiments with various model families and tasks, we discover a scaling phenomenon of self-improvement -- a variant of the generation-verification gap scales monotonically with the model pre-training flops. We also examine when self-improvement is possible, an iterative self-improvement procedure, and ways to improve its performance. Our findings not only advance understanding of LLM self-improvement with practical implications, but also open numerous avenues for future research into its capabilities and boundaries.