Automatic Model Selection with Large Language Models for Reasoning

James Xu Zhao, Yuxi Xie, Kenji Kawaguchi, Junxian He, Michael Qizhe Xie

Submission Type: Regular Long Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Submission Track 2: Commonsense Reasoning

Keywords: Large Language Models, In-Context Learning, Reasoning

TL;DR: We propose a model selection method to combine two distinct reasoning models, CoT and PAL, and achieve the new SOTA results on GSM8K and SVAMP.

Abstract: Chain-of-Thought (CoT) and Program-Aided Language Models (PAL) represent two distinct reasoning methods, each with its own strengths. CoT employs natural language, offering flexibility and interpretability, while PAL utilizes programming language, yielding more structured and rigorous logic. We introduce a model selection method to combine the best of both worlds by employing a large language model (LLM) to dynamically select between them. Our theoretical analysis underscores the feasibility of this method, which is further corroborated by empirical results. Our proposed method demonstrates significant performance improvements across eight reasoning datasets with Codex, ChatGPT, and GPT-4. Additionally, our method is complementary to self-consistency; when integrated, it can further enhance performance while significantly reducing computation costs. Moreover, we achieve new state-of-the-art results on GSM8K and SVAMP, with respective accuracies of 96.8% and 93.7%.

Submission Number: 553