# Text summarization via global structure awareness

arXiv: https://arxiv.org/abs/2602.09821 · HTML: https://mlsanity.com/paper/2602.09821/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [On the Use of ArXiv as a Dataset](https://mlsanity.com/paper/1905.00075/) (2019)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [DebateSum: A large-scale argument mining and summarization dataset](https://mlsanity.com/paper/2011.07251/) (2020)
- [DeepZip: Lossless Data Compression using Recurrent Neural Networks](https://mlsanity.com/paper/1811.08162/) (2018)
- [MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes](https://mlsanity.com/paper/2107.08929/) (2021)
- [FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression](https://mlsanity.com/paper/2409.17141/) (2024)
- [LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations](https://mlsanity.com/paper/2503.10658/) (2025)
- [LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models](https://mlsanity.com/paper/2602.00135/) (2026)
- [TexShape: Information Theoretic Sentence Embedding for Language Models](https://mlsanity.com/paper/2402.05132/) (2024)
- [Lightweight Medical Image Restoration via Integrating Reliable Lesion-Semantic Driven Prior](https://mlsanity.com/paper/2504.11286/) (2025)
- [Can BERT eat RuCoLA? Topological Data Analysis to Explain](https://mlsanity.com/paper/2304.01680/) (2023)
- [Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction](https://mlsanity.com/paper/2505.06297/) (2025)
- [Unsupervised Extractive Summarization with Learnable Length Control Strategies](https://mlsanity.com/paper/2312.06901/) (2023)

## Built on by (most cited first, 12 of 12)

- [Lightweight LLM Agent Memory with Small Language Models](https://mlsanity.com/paper/2604.07798/) (2026)
- [StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding](https://mlsanity.com/paper/2604.09000/) (2026)
- [Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization](https://mlsanity.com/paper/2604.07165/) (2026)
- [Experience Transfer for Multimodal LLM Agents in Minecraft Game](https://mlsanity.com/paper/2604.05533/) (2026)
- [Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization](https://mlsanity.com/paper/2603.12933/) (2026)
- [Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs](https://mlsanity.com/paper/2604.12610/) (2026)
- [Rethinking Input Domains in Physics-Informed Neural Networks via Geometric Compactification Mappings](https://mlsanity.com/paper/2602.16193/) (2026)
- [Weak-Link Optimization for Multi-Agent Reasoning and Collaboration](https://mlsanity.com/paper/2604.15972/) (2026)
- [DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing](https://mlsanity.com/paper/2604.19351/) (2026)
- [From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors](https://mlsanity.com/paper/2604.23277/) (2026)
- [Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models](https://mlsanity.com/paper/2604.18612/) (2026)
- [Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking](https://mlsanity.com/paper/2606.01240/) (2026)

## Abstract (arXiv)

Text summarization is a fundamental task in natural language processing (NLP), and the information explosion has made long-document processing increasingly demanding, making summarization essential. Existing research mainly focuses on model improvements and sentence-level pruning, but often overlooks global structure, leading to disrupted coherence and weakened downstream performance. Some studies employ large language models (LLMs), which achieve higher accuracy but incur substantial resource and time costs. To address these issues, we introduce GloSA-sum, the first summarization approach that achieves global structure awareness via topological data analysis (TDA). GloSA-sum summarizes text efficiently while preserving semantic cores and logical dependencies. Specifically, we construct a semantic-weighted graph from sentence embeddings, where persistent homology identifies core semantics and logical structures, preserved in a ``protection pool'' as the backbone for summarization. We design a topology-guided iterative strategy, where lightweight proxy metrics approximate sentence importance to avoid repeated high-cost computations, thus preserving structural integrity while improving efficiency. To further enhance long-text processing, we propose a hierarchical strategy that integrates segment-level and global summarization. Experiments on multiple datasets demonstrate that GloSA-sum reduces redundancy while preserving semantic and logical integrity, striking a balance between accuracy and efficiency, and further benefits LLM downstream tasks by shortening contexts while retaining essential reasoning chains.