Leveraging Hierarchical Organization for Medical Multi-document Summarization

• URL: http://arxiv.org/abs/2510.23104v2
• Date: Tue, 04 Nov 2025 06:31:49 GMT
• Title: Leveraging Hierarchical Organization for Medical Multi-document Summarization
• Authors: Yi-Li Hsu, Katelyn X. Mei, Lucy Lu Wang,
• Abstract summary: We investigate whether incorporating hierarchical structures in the inputs of medical multi-document summarization can improve a model's ability to organize and contextualize information across documents.<n>Our results show that human experts prefer model-generated summaries over human-written summaries.
• Score: 9.907620975399185
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical multi-document summarization (MDS) is a complex task that requires effectively managing cross-document relationships. This paper investigates whether incorporating hierarchical structures in the inputs of MDS can improve a model's ability to organize and contextualize information across documents compared to traditional flat summarization methods. We investigate two ways of incorporating hierarchical organization across three large language models (LLMs), and conduct comprehensive evaluations of the resulting summaries using automated metrics, model-based metrics, and domain expert evaluation of preference, understandability, clarity, complexity, relevance, coverage, factuality, and coherence. Our results show that human experts prefer model-generated summaries over human-written summaries. Hierarchical approaches generally preserve factuality, coverage, and coherence of information, while also increasing human preference for summaries. Additionally, we examine whether simulated judgments from GPT-4 align with human judgments, finding higher agreement along more objective evaluation facets. Our findings demonstrate that hierarchical structures can improve the clarity of medical summaries generated by models while maintaining content coverage, providing a practical way to improve human preference for generated summaries.

Related papers

• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
  Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
  arXiv  Detail & Related papers  (2025-10-17T02:33:16Z)
• Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization [86.98098988779809]
  We propose SummQ, a novel adversarial multi-agent framework for long document summarization.<n>Our approach employs summary generators and reviewers that work collaboratively to create and evaluate comprehensive summaries.<n>We evaluate SummQ on three widely used long document summarization benchmarks.
  arXiv  Detail & Related papers  (2025-09-25T08:36:19Z)
• Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering [59.54662810933882]
  Existing taxonomy construction methods, leveraging unsupervised clustering or direct prompting of large language models, often lack coherence and granularity.<n>We propose a novel context-aware hierarchical taxonomy generation framework that integrates LLM-guided multi-aspect encoding with dynamic clustering.
  arXiv  Detail & Related papers  (2025-09-23T15:12:58Z)
• MRGSEM-Sum: An Unsupervised Multi-document Summarization Framework based on Multi-Relational Graphs and Structural Entropy Minimization [15.596156608713347]
  MRGSEM-Sum is an unsupervised multi-document summarization framework based on multi-relational graphs and structural entropy minimization.<n>We introduce a position-aware compression mechanism to distill each cluster, generating concise and informative summaries.
  arXiv  Detail & Related papers  (2025-07-31T10:14:03Z)
• GEGA: Graph Convolutional Networks and Evidence Retrieval Guided Attention for Enhanced Document-level Relation Extraction [15.246183329778656]
  Document-level relation extraction (DocRE) aims to extract relations between entities from unstructured document text. To overcome these challenges, we propose GEGA, a novel model for DocRE. We evaluate the GEGA model on three widely used benchmark datasets: DocRED, Re-DocRED, and Revisit-DocRED.
  arXiv  Detail & Related papers  (2024-07-31T07:15:33Z)
• Hierarchical Indexing for Retrieval-Augmented Opinion Summarization [60.5923941324953]
  We propose a method for unsupervised abstractive opinion summarization that combines the attributability and scalability of extractive approaches with the coherence and fluency of Large Language Models (LLMs) Our method, HIRO, learns an index structure that maps sentences to a path through a semantically organized discrete hierarchy. At inference time, we populate the index and use it to identify and retrieve clusters of sentences containing popular opinions from input reviews.
  arXiv  Detail & Related papers  (2024-03-01T10:38:07Z)
• Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation [45.9443710073576]
  We present PeerSum, a novel dataset for generating meta-reviewes of scientific papers. Rammer is a model that uses sparse attention based on the conversational structure and a training objective that predicts metadata features.
  arXiv  Detail & Related papers  (2023-05-02T15:18:18Z)
• How to Find Strong Summary Coherence Measures? A Toolbox and a Comparative Study for Summary Coherence Measure Evaluation [3.434197496862117]
  We conduct a large-scale investigation of various methods for summary coherence modelling on an even playing field. We introduce two novel analysis measures, intra-system correlation and bias matrices, that help identify biases in coherence measures and provide robustness against system-level confounders. While none of the currently available automatic coherence measures are able to assign reliable coherence scores to system summaries across all evaluation metrics, large-scale language models show promising results, as long as fine-tuning takes into account that they need to generalize across different summary lengths.
  arXiv  Detail & Related papers  (2022-09-14T09:42:19Z)
• Parallel Hierarchical Transformer with Attention Alignment for Abstractive Multi-Document Summarization [4.035753155957699]
  Abstractive Multi-Document Summarization (MDS) brings challenges on the representation and coverage of its lengthy and linked sources. This study develops a Parallel Hierarchical Transformer (PHT) with attention alignment for MDS.
  arXiv  Detail & Related papers  (2022-08-16T17:02:48Z)
• SummEval: Re-evaluating Summarization Evaluation [169.622515287256]
  We re-evaluate 14 automatic evaluation metrics in a comprehensive and consistent fashion. We benchmark 23 recent summarization models using the aforementioned automatic evaluation metrics. We assemble the largest collection of summaries generated by models trained on the CNN/DailyMail news dataset.
  arXiv  Detail & Related papers  (2020-07-24T16:25:19Z)

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.