Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models
This addresses the issue of unreliable reasoning in LLMs for users needing robust AI reasoning, though it is incremental as it builds on existing CoT prompting.
The paper tackles the problem of errors in chain-of-thought prompting for large language models by introducing Iter-CoT, an iterative bootstrapping method that autonomously corrects errors and selects optimal exemplars, achieving competitive performance on three reasoning tasks across ten datasets.
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by LLMs are prone to errors, which can subsequently lead to incorrect reasoning during inference. Furthermore, inappropriate exemplars (overly simplistic or complex), can affect overall performance among varying levels of difficulty. We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains. By utilizing iterative bootstrapping, our approach enables LLMs to autonomously rectify errors, resulting in more precise and comprehensive reasoning chains. Simultaneously, our approach selects challenging yet answerable questions accompanied by reasoning chains as exemplars with a moderate level of difficulty, which enhances the LLMs' generalizability across varying levels of difficulty. Experimental results indicate that Iter-CoT exhibits superiority, achieving competitive performance across three distinct reasoning tasks on ten datasets.