Salvato in:
Dettagli Bibliografici
Autori principali: Luo, Guanran, Jian, Zhongquan, Qiu, Wentao, Wang, Meihong, Wu, Qingqiang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.07012
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914457913917440
author Luo, Guanran
Jian, Zhongquan
Qiu, Wentao
Wang, Meihong
Wu, Qingqiang
author_facet Luo, Guanran
Jian, Zhongquan
Qiu, Wentao
Wang, Meihong
Wu, Qingqiang
contents Retrieval-Augmented Generation (RAG) mitigates the hallucination problem of Large Language Models (LLMs) by incorporating external knowledge. Recursive summarization constructs a hierarchical summary tree by clustering text chunks, integrating information from multiple parts of a document to provide evidence for abstractive questions involving multi-step reasoning. However, summary trees often contain a large number of redundant summary nodes, which not only increase construction time but may also negatively impact question answering. Moreover, recursive summarization is not suitable for all types of questions. We introduce DTCRS, a method that dynamically generates summary trees based on document structure and query semantics. DTCRS determines whether a summary tree is necessary by analyzing the question type. It then decomposes the question and uses the embeddings of sub-questions as initial cluster centers, reducing redundant summaries while improving the relevance between summaries and the question. Our approach significantly reduces summary tree construction time and achieves substantial improvements across three QA tasks. Additionally, we investigate the applicability of recursive summarization to different question types, providing valuable insights for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07012
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DTCRS: Dynamic Tree Construction for Recursive Summarization
Luo, Guanran
Jian, Zhongquan
Qiu, Wentao
Wang, Meihong
Wu, Qingqiang
Computation and Language
Retrieval-Augmented Generation (RAG) mitigates the hallucination problem of Large Language Models (LLMs) by incorporating external knowledge. Recursive summarization constructs a hierarchical summary tree by clustering text chunks, integrating information from multiple parts of a document to provide evidence for abstractive questions involving multi-step reasoning. However, summary trees often contain a large number of redundant summary nodes, which not only increase construction time but may also negatively impact question answering. Moreover, recursive summarization is not suitable for all types of questions. We introduce DTCRS, a method that dynamically generates summary trees based on document structure and query semantics. DTCRS determines whether a summary tree is necessary by analyzing the question type. It then decomposes the question and uses the embeddings of sub-questions as initial cluster centers, reducing redundant summaries while improving the relevance between summaries and the question. Our approach significantly reduces summary tree construction time and achieves substantial improvements across three QA tasks. Additionally, we investigate the applicability of recursive summarization to different question types, providing valuable insights for future research.
title DTCRS: Dynamic Tree Construction for Recursive Summarization
topic Computation and Language
url https://arxiv.org/abs/2604.07012