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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Xinyue, Gao, Pengyu, Song, Jiangjiang, Tan, Xiaoyang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908059050180608
author Chen, Xinyue
Gao, Pengyu
Song, Jiangjiang
Tan, Xiaoyang
author_facet Chen, Xinyue
Gao, Pengyu
Song, Jiangjiang
Tan, Xiaoyang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_01767
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA
Chen, Xinyue
Gao, Pengyu
Song, Jiangjiang
Tan, Xiaoyang
Computation and Language
Artificial Intelligence
Machine Learning
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.
title HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.01767