SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models
This work addresses the problem of enhancing Large Language Models' reasoning capabilities for Natural Language Processing tasks, which is significant for researchers and developers relying on these models for complex question-answering tasks.
The researchers tackled the problem of improving Large Language Models' reasoning capabilities and achieved significant results, surpassing traditional chain-of-thought prompts and existing rephrase-and-respond methods. SQuARE promotes a more thorough exploration of various aspects of a topic by generating and resolving multiple auxiliary questions before tackling the main query.
In the rapidly evolving field of Natural Language Processing, Large Language Models (LLMs) are tasked with increasingly complex reasoning challenges. Traditional methods like chain-of-thought prompting have shown promise but often fall short in fully leveraging a model's reasoning capabilities. This paper introduces SQuARE (Sequential Question Answering Reasoning Engine), a novel prompting technique designed to improve reasoning through a self-interrogation paradigm. Building upon CoT frameworks, SQuARE prompts models to generate and resolve multiple auxiliary questions before tackling the main query, promoting a more thorough exploration of various aspects of a topic. Our expansive evaluations, conducted with Llama 3 and GPT-4o models across multiple question-answering datasets, demonstrate that SQuARE significantly surpasses traditional CoT prompts and existing rephrase-and-respond methods. By systematically decomposing queries, SQuARE advances LLM capabilities in reasoning tasks. The code is publicly available at https://github.com/IntelLabs/RAG-FiT/tree/square.