MoT: Memory-of-Thought Enables ChatGPT to Self-Improve
Submission Type: Regular Long Paper
Submission Track: Theme Track: Large Language Models and the Future of NLP
Submission Track 2: NLP Applications
Keywords: LLM, ChatGPT, Self-Improve, Large Language Model, Memory
TL;DR: MoT: Memory-of-Thought Enables ChatGPT to Self-Improve
Abstract: Large Language Models (LLMs) have shown impressive abilities on various tasks. However, fundamentally improving them depends on high-quality datasets or computationally expensive fine-tuning. On the contrary, humans can easily improve themselves by self-thinking and memory, without external resources. In this paper, we propose a framework, **MoT**, to let the LLM self-improve through **M**emory **o**f **T**houghts, without annotated datasets and parameter updates. Specifically, MoT is divided into two stages: 1. before the test stage, the LLM pre-thinks on the unlabeled dataset and saves the high-confidence thoughts as external memory; 2. During the test stage, given a test question, the LLM recalls relevant memory to help itself reason and answer it. Experimental results show that MoT can help ChatGPT significantly improve its abilities in arithmetic reasoning, commonsense reasoning, factual reasoning, and natural language inference. Further analyses show that each component contributes critically to the improvements and MoT can lead to consistent improvements across various CoT methods and LLMs.
Submission Number: 470
Loading