ProofSketch: Efficient Verified Reasoning for Large Language Models
This addresses computational cost and latency issues for users of large language models in reasoning tasks, though it appears incremental as it builds on existing reasoning methods.
The paper tackles the inefficiency of reasoning methods like chain-of-thought prompting in large language models, which increase token usage and latency, by proposing ProofSketch, a verification-guided framework that reduces token consumption and improves accuracy.
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.