<ul><li>Large Language Models still encounter challenges in reasoning tasks, especially for smaller models.</li><li>Inference-time methods like prompting have shown effectiveness but rely on sequential queries.</li><li>The ensemble method, running multiple models in parallel, is a promising approach for better inference-time performance.</li><li>A novel training-free LLM ensemble framework is proposed for improved reasoning in math tasks.</li></ul>

Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks

Discover more