AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning
This addresses limitations in QA systems for general and domain-specific tasks like medical QA, though it appears incremental as it builds on existing RAG methods with topic filtering.
The paper tackles the problem of handling complex multi-hop queries in QA with LLMs by proposing AT-RAG, which uses topic modeling and iterative reasoning to improve retrieval efficiency and accuracy, resulting in significant improvements in correctness, completeness, and relevance while reducing retrieval time.
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.