Zero-Shot Verification-guided Chain of Thoughts

TL;DR

This paper introduces a zero-shot approach for LLM-based self-verification of reasoning steps in Chain-of-Thought prompting, eliminating the need for fine-tuning or manual examples, and evaluates its effectiveness across reasoning tasks.

Contribution

The paper proposes new zero-shot prompts for reasoning decomposition and verification, enabling LLMs to self-assess reasoning correctness without prior training or handcrafted examples.

Findings

Zero-shot verifiers can classify reasoning correctness effectively.

Verifier scores can guide reasoning processes.

Method improves reasoning accuracy in mathematical and commonsense tasks.

Abstract

Previous works have demonstrated the effectiveness of Chain-of-Thought (COT) prompts and verifiers in guiding Large Language Models (LLMs) through the space of reasoning. However, most such studies either use a fine-tuned verifier or rely on manually handcrafted few-shot examples. In contrast, in this paper, we focus on LLM-based self-verification of self-generated reasoning steps via COT prompts in a completely zero-shot regime. To explore this setting, we design a new zero-shot prompt, which we call COT STEP, to aid zero-shot decomposition of reasoning steps and design two new zero-shot prompts for LLM-based verifiers. We evaluate the verifiers' ability to classify the correctness of reasoning chains and explore different ways to use verifier scores in guiding reasoning for various mathematical and commonsense reasoning tasks with different LLMs.