AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning

TL;DR

AT-RAG is an innovative multi-step retrieval-augmented generation model that uses topic filtering and iterative reasoning to improve efficiency and accuracy in complex multi-hop question answering tasks.

Contribution

It introduces a novel approach combining topic modeling with iterative reasoning to enhance document retrieval and answer accuracy in multi-hop QA.

Findings

Significant improvements in correctness, completeness, and relevance.

Reduces retrieval time while maintaining high precision.

Effective in both general and domain-specific QA tasks.

Abstract

Recent advancements in QA with LLM, like GPT-4, have shown limitations in handling complex multi-hop queries. We propose AT-RAG, a novel multistep RAG incorporating topic modeling for efficient document retrieval and reasoning. Using BERTopic, our model dynamically assigns topics to queries, improving retrieval accuracy and efficiency. We evaluated AT-RAG on multihop benchmark datasets QA and a medical case study QA. Results show significant improvements in correctness, completeness, and relevance compared to existing methods. AT-RAG reduces retrieval time while maintaining high precision, making it suitable for general tasks QA and complex domain-specific challenges such as medical QA. The integration of topic filtering and iterative reasoning enables our model to handle intricate queries efficiently, which makes it suitable for applications that require nuanced information retrieval and decision-making.