ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Roy, Kashob Kumar, Akash, Pritom Saha, Chang, Kevin Chen-Chuan, Popa, Lucian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916447682297856
author Roy, Kashob Kumar
Akash, Pritom Saha
Chang, Kevin Chen-Chuan
Popa, Lucian
author_facet Roy, Kashob Kumar
Akash, Pritom Saha
Chang, Kevin Chen-Chuan
Popa, Lucian
contents Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth. This task is challenging due to the need to accurately capture diverse facets of input queries. Existing iterative retrieval-augmented generation (RAG) approaches often struggle to delve deeply into each facet of complex queries and integrate knowledge from various sources effectively. This paper introduces ConTReGen, a novel framework that employs a context-driven, tree-structured retrieval approach to enhance the depth and relevance of retrieved content. ConTReGen integrates a hierarchical, top-down in-depth exploration of query facets with a systematic bottom-up synthesis, ensuring comprehensive coverage and coherent integration of multifaceted information. Extensive experiments on multiple datasets, including LFQA and ODSUM, alongside a newly introduced dataset, ODSUM-WikiHow, demonstrate that ConTReGen outperforms existing state-of-the-art RAG models.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15511
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation
Roy, Kashob Kumar
Akash, Pritom Saha
Chang, Kevin Chen-Chuan
Popa, Lucian
Information Retrieval
Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth. This task is challenging due to the need to accurately capture diverse facets of input queries. Existing iterative retrieval-augmented generation (RAG) approaches often struggle to delve deeply into each facet of complex queries and integrate knowledge from various sources effectively. This paper introduces ConTReGen, a novel framework that employs a context-driven, tree-structured retrieval approach to enhance the depth and relevance of retrieved content. ConTReGen integrates a hierarchical, top-down in-depth exploration of query facets with a systematic bottom-up synthesis, ensuring comprehensive coverage and coherent integration of multifaceted information. Extensive experiments on multiple datasets, including LFQA and ODSUM, alongside a newly introduced dataset, ODSUM-WikiHow, demonstrate that ConTReGen outperforms existing state-of-the-art RAG models.
title ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation
topic Information Retrieval
url https://arxiv.org/abs/2410.15511