Explanations from Large Language Models Make Small Reasoners Better
This addresses the need for efficient, explainable AI in real-production deployments by enhancing small models' reasoning capabilities.
The paper tackles the problem of improving small reasoning models by leveraging explanations from large language models, resulting in consistent and significant performance gains over baselines, including up to 9.5% higher accuracy than a much larger GPT-3 model.
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the explanations generated by LLM to improve the training of small reasoners, which are more favorable in real-production deployment due to their low cost. We systematically explore three explanation generation approaches from LLM and utilize a multi-task learning framework to facilitate small models to acquire strong reasoning power together with explanation generation capabilities. Experiments on multiple reasoning tasks show that our method can consistently and significantly outperform finetuning baselines across different settings, and even perform better than finetuning/prompting a 60x larger GPT-3 (175B) model by up to 9.5% in accuracy. As a side benefit, human evaluation further shows that our method can generate high-quality explanations to justify its predictions, moving towards the goal of explainable AI.