HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
This addresses inefficiencies and noise issues in RAG systems for multi-hop QA, offering a domain-specific improvement for question-answering tasks.
The paper tackles the problem of noise accumulation and inefficiency in multi-hop question answering with Retrieval-Augmented Generation (RAG) by introducing HANRAG, a heuristic-based framework that routes queries, decomposes them into sub-queries, and filters noise, achieving superior performance on benchmarks compared to leading methods.
The Retrieval-Augmented Generation (RAG) approach enhances question-answering systems and dialogue generation tasks by integrating information retrieval (IR) technologies with large language models (LLMs). This strategy, which retrieves information from external knowledge bases to bolster the response capabilities of generative models, has achieved certain successes. However, current RAG methods still face numerous challenges when dealing with multi-hop queries. For instance, some approaches overly rely on iterative retrieval, wasting too many retrieval steps on compound queries. Additionally, using the original complex query for retrieval may fail to capture content relevant to specific sub-queries, resulting in noisy retrieved content. If the noise is not managed, it can lead to the problem of noise accumulation. To address these issues, we introduce HANRAG, a novel heuristic-based framework designed to efficiently tackle problems of varying complexity. Driven by a powerful revelator, HANRAG routes queries, decomposes them into sub-queries, and filters noise from retrieved documents. This enhances the system's adaptability and noise resistance, making it highly capable of handling diverse queries. We compare the proposed framework against other leading industry methods across various benchmarks. The results demonstrate that our framework obtains superior performance in both single-hop and multi-hop question-answering tasks.