HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA

TL;DR

HiQA introduces a hierarchical, multi-route retrieval framework with cascading metadata for multi-document QA, achieving state-of-the-art accuracy and reliability in complex document environments.

Contribution

The paper presents HiQA, a novel multi-document QA framework with cascading metadata and multi-route retrieval, and introduces the MasQA benchmark for evaluation.

Findings

HiQA outperforms existing methods in multi-document QA accuracy.

The multi-route retrieval mechanism improves retrieval precision.

MasQA benchmark facilitates research in multi-document QA.

Abstract

Retrieval-augmented generation (RAG) has rapidly advanced the language model field, particularly in question-answering (QA) systems. By integrating external documents during the response generation phase, RAG significantly enhances the accuracy and reliability of language models. This method elevates the quality of responses and reduces the frequency of hallucinations, where the model generates incorrect or misleading information. However, these methods exhibit limited retrieval accuracy when faced with numerous indistinguishable documents, presenting notable challenges in their practical application. In response to these emerging challenges, we present HiQA, an advanced multi-document question-answering (MDQA) framework that integrates cascading metadata into content and a multi-route retrieval mechanism. We also release a benchmark called MasQA to evaluate and research in MDQA. Finally, HiQA demonstrates the state-of-the-art performance in multi-document environments.