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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rezaei, Mohammad Reza, Hafezi, Maziar, Satpathy, Amit, Hodge, Lovell, Pourjafari, Ebrahim
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910653906681856
author Rezaei, Mohammad Reza
Hafezi, Maziar
Satpathy, Amit
Hodge, Lovell
Pourjafari, Ebrahim
author_facet Rezaei, Mohammad Reza
Hafezi, Maziar
Satpathy, Amit
Hodge, Lovell
Pourjafari, Ebrahim
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12886
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning
Rezaei, Mohammad Reza
Hafezi, Maziar
Satpathy, Amit
Hodge, Lovell
Pourjafari, Ebrahim
Computation and Language
Information Retrieval
Machine Learning
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.
title AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning
topic Computation and Language
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2410.12886