ProofSketch: Efficient Verified Reasoning for Large Language Models

TL;DR

ProofSketch is a verification-guided reasoning framework for large language models that reduces token usage and improves accuracy by integrating symbolic verification and adaptive sketch generation.

Contribution

It introduces a novel verification-guided reasoning method combining symbolic closure, lexicographic verification, and adaptive sketching to enhance efficiency and trustworthiness.

Findings

Reduces token consumption in reasoning tasks

Improves reasoning accuracy over baseline methods

Demonstrates efficiency and trustworthiness in experiments

Abstract

Reasoning methods such as chain-of-thought prompting and self-consistency have shown immense potential to improve the accuracy of large language models across various reasoning tasks. However such methods involve generation of lengthy reasoning chains, which substantially increases token consumption, computational cost, and latency. To address this inefficiency, we propose ProofSketch, a verification-guided reasoning framework that integrates symbolic closure computation, lexicographic verification and adaptive sketch generation. Our experiments show that ProofSketch consistently reduces token usage while improving accuracy, demonstrating that this approach offers a promising path for efficient and trustworthy reasoning.