General Purpose Verification for Chain of Thought Prompting

TL;DR

This paper enhances the reasoning capabilities of Large Language Models by applying verification principles to their generated reasoning steps, improving accuracy across multiple reasoning tasks.

Contribution

It introduces a verification-based approach using relevance, accuracy, and consistency constraints, along with perplexity scoring, to improve LLM reasoning performance.

Findings

Outperforms vanilla generation on all tested datasets.

Surpasses best-of N sampling in 6 out of 9 datasets.

Improves reasoning accuracy through step verification and perplexity scoring.

Abstract

Many of the recent capabilities demonstrated by Large Language Models (LLMs) arise primarily from their ability to exploit contextual information. In this paper, we explore ways to improve reasoning capabilities of LLMs through (1) exploration of different chains of thought and (2) validation of the individual steps of the reasoning process. We propose three general principles that a model should adhere to while reasoning: (i) Relevance, (ii) Mathematical Accuracy, and (iii) Logical Consistency. We apply these constraints to the reasoning steps generated by the LLM to improve the accuracy of the final generation. The constraints are applied in the form of verifiers: the model itself is asked to verify if the generated steps satisfy each constraint. To further steer the generations towards high-quality solutions, we use the perplexity of the reasoning steps as an additional verifier. We evaluate our method on 4 distinct types of reasoning tasks, spanning a total of 9 different datasets. Experiments show that our method is always better than vanilla generation, and, in 6 out of the 9 datasets, it is better than best-of N sampling which samples N reasoning chains and picks the lowest perplexity generation.