DTCRS: Dynamic Tree Construction for Recursive Summarization

• URL: http://arxiv.org/abs/2604.07012v1
• Date: Wed, 08 Apr 2026 12:33:42 GMT
• Title: DTCRS: Dynamic Tree Construction for Recursive Summarization
• Abstract summary: We introduce DTCRS, a method that generates summary trees based on document structure and query semantics.<n>Our approach significantly reduces summary tree construction time and achieves substantial improvements across three QA tasks.
• Score: 12.903751268469698
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Segment-level Tree Search for Long Meeting Document Summarization [40.841609062628216]
  We propose segment-level summarization via Monte Carlo Tree Search (S3), a training-free framework.<n>S3 partitions a long document into segments and generates multiple summary candidates per segment, forming nodes of a search tree.<n>Despite using a 7B model, S3 achieves performance comparable to larger 72B models while producing length-appropriate summaries.
  arXiv  Detail & Related papers  (2026-06-07T04:21:23Z)
• MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries [2.756584457554517]
  Map-Disambiguate-Enrich-Reduce (MDER) generates context-derived triple descriptions and integrates them with entity-level summaries.<n>Decompose-Resolve (DR) decomposes user queries into resolvable triples and grounds them in the Knowledge Graph.<n>MDER and DR form an LLM-driven QA pipeline that is robust to sparse, incomplete, and complex relational data.
  arXiv  Detail & Related papers  (2026-03-11T18:38:44Z)
• TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation [17.21708416305234]
  textscTaSR-RAG is a taxonomy-guided structured reasoning framework for evidence selection.<n>textscTaSR-RAG consistently outperforms strong RAG and structured-RAG baselines by up to 14%.
  arXiv  Detail & Related papers  (2026-03-10T08:16:36Z)
• Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval [68.71038700559195]
  Chain of Retrieval(COR) is a novel iterative framework for full-paper retrieval.<n>We present SCIBENCH, a benchmark providing both complete and segmented contexts of full papers for queries and candidates.
  arXiv  Detail & Related papers  (2025-07-14T08:41:53Z)
• TreeRare: Syntax Tree-Guided Retrieval and Reasoning for Knowledge-Intensive Question Answering [10.597526246308938]
  Iterative and adaptive retrieval has been shown to be a promising approach to resolve complex, knowledge-intensive questions.<n>We propose TreeRare, a framework that utilizes syntax trees to guide information retrieval and reasoning for question answering.<n>TreeRare achieves substantial improvements over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-31T01:07:50Z)
• Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering [51.7493726399073]
  We present a discourse-aware hierarchical framework to enhance long document question answering.<n>The framework involves three key innovations: specialized discourse parsing for lengthy documents, LLM-based enhancement of discourse relation nodes, and structure-guided hierarchical retrieval.
  arXiv  Detail & Related papers  (2025-05-26T14:45:12Z)
• Context-Aware Hierarchical Merging for Long Document Summarization [56.96619074316232]
  We propose different approaches to enrich hierarchical merging with context from the source document.<n> Experimental results on datasets representing legal and narrative domains show that contextual augmentation consistently outperforms zero-shot and hierarchical merging baselines.
  arXiv  Detail & Related papers  (2025-02-03T01:14:31Z)
• RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval [26.527911244587134]
  We introduce the novel approach of embedding, clustering, and summarizing chunks of text, constructing a tree with differing levels of summarization from the bottom up. At inference time, our RAPTOR model retrieves from this tree, integrating information across lengthy documents at different levels of abstraction.
  arXiv  Detail & Related papers  (2024-01-31T18:30:21Z)
• Successive Prompting for Decomposing Complex Questions [50.00659445976735]
  Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting. We introduce Successive Prompting'', where we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Our best model (with successive prompting) achieves an improvement of 5% absolute F1 on a few-shot version of the DROP dataset.
  arXiv  Detail & Related papers  (2022-12-08T06:03:38Z)
• Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner [56.08919422452905]
  We propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR) Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. We outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.
  arXiv  Detail & Related papers  (2022-05-18T21:52:11Z)
• HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization [17.58231642569116]
  We present HIBRIDS, which injects Hierarchical Biases foR incorporating Document Structure into the calculation of attention scores. We also present a new task, hierarchical question-summary generation, for summarizing salient content in the source document into a hierarchy of questions and summaries.
  arXiv  Detail & Related papers  (2022-03-21T05:27:35Z)
• Abstractive Query Focused Summarization with Query-Free Resources [60.468323530248945]
  In this work, we consider the problem of leveraging only generic summarization resources to build an abstractive QFS system. We propose Marge, a Masked ROUGE Regression framework composed of a novel unified representation for summaries and queries. Despite learning from minimal supervision, our system achieves state-of-the-art results in the distantly supervised setting.
  arXiv  Detail & Related papers  (2020-12-29T14:39:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.