Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction
This addresses the challenge of improving self-reflection in LLMs for better reasoning performance, though it appears incremental as it builds on existing reflection approaches.
The paper tackles the problem of static reflection methods in large language models causing redundant, drift, and stubborn issues, and introduces Instruct-of-Reflection (IoRT), a framework using dynamic-meta instruction to enhance iterative reflection, achieving an average 10.1% improvement over baselines in mathematical and commonsense reasoning tasks.
Self-reflection for Large Language Models (LLMs) has gained significant attention. Existing approaches involve models iterating and improving their previous responses based on LLMs' internal reflection ability or external feedback. However, recent research has raised doubts about whether intrinsic self-correction without external feedback may even degrade performance. Based on our empirical evidence, we find that current static reflection methods may lead to redundant, drift, and stubborn issues. To mitigate this, we introduce Instruct-of-Reflection (IoRT), a novel and general reflection framework that leverages dynamic-meta instruction to enhance the iterative reflection capability of LLMs. Specifically, we propose the instructor driven by the meta-thoughts and self-consistency classifier, generates various instructions, including refresh, stop, and select, to guide the next reflection iteration. Our experiments demonstrate that IoRT achieves an average improvement of 10.1% over established baselines in mathematical and commonsense reasoning tasks, highlighting its efficacy and applicability.