# Examining the State-of-the-Art in News Timeline Summarization

arXiv: https://arxiv.org/abs/2005.10107 · HTML: https://mlsanity.com/paper/2005.10107/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2020.

## Built on by (most cited first, 27 of 27)

- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding](https://mlsanity.com/paper/2406.02472/) (2024)
- [A Survey on Event-based News Narrative Extraction](https://mlsanity.com/paper/2302.08351/) (2023)
- [CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization](https://mlsanity.com/paper/2210.14190/) (2022)
- [PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream](https://mlsanity.com/paper/2302.05550/) (2023)
- [Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance](https://mlsanity.com/paper/2412.17408/) (2024)
- [Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order](https://mlsanity.com/paper/2301.00867/) (2023)
- [TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System](https://mlsanity.com/paper/2109.05187/) (2021)
- [Incremental Extractive Opinion Summarization Using Cover Trees](https://mlsanity.com/paper/2401.08047/) (2024)
- [Video Timeline Modeling For News Story Understanding](https://mlsanity.com/paper/2309.13446/) (2023)
- [CNTLS: A Benchmark Dataset for Abstractive or Extractive Chinese Timeline Summarization](https://mlsanity.com/paper/2105.14201/) (2021)
- [Archive TimeLine Summarization (ATLS): Conceptual Framework for Timeline Generation over Historical Document Collections](https://mlsanity.com/paper/2301.13479/) (2023)
- [Background Summarization of Event Timelines](https://mlsanity.com/paper/2310.16197/) (2023)
- [Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events](https://mlsanity.com/paper/2408.04873/) (2024)
- [How News Evolves? Modeling News Text and Coverage using Graphs and Hawkes Process](https://mlsanity.com/paper/2112.03008/) (2021)
- [Placing (Historical) Facts on a Timeline: A Classification cum Coref Resolution Approach](https://mlsanity.com/paper/2206.14089/) (2022)
- [Towards Abstractive Timeline Summarisation using Preference-based Reinforcement Learning](https://mlsanity.com/paper/2211.07596/) (2022)
- [News Signals: An NLP Library for Text and Time Series](https://mlsanity.com/paper/2312.11399/) (2023)
- [Distilling Event Sequence Knowledge From Large Language Models](https://mlsanity.com/paper/2401.07237/) (2024)
- [TLEX: An Efficient Method for Extracting Exact Timelines from TimeML Temporal Graphs](https://mlsanity.com/paper/2406.05265/) (2024)
- [Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization](https://mlsanity.com/paper/2406.05361/) (2024)
- [TIM: A Large-Scale Dataset and large Timeline Intelligence Model for Open-domain Timeline Summarization](https://mlsanity.com/paper/2506.21616/) (2025)
- [Who's important? -- SUnSET: Synergistic Understanding of Stakeholder, Events and Time for Timeline Generation](https://mlsanity.com/paper/2507.21903/) (2025)
- [Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search](https://mlsanity.com/paper/2605.27066/) (2026)
- [NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning](https://mlsanity.com/paper/2606.13171/) (2026)
- [Query-Focused Event Summarization: A Dataset and Benchmark](https://mlsanity.com/paper/2607.11166/) (2026)

## Abstract (arXiv)

Previous work on automatic news timeline summarization (TLS) leaves an unclear picture about how this task can generally be approached and how well it is currently solved. This is mostly due to the focus on individual subtasks, such as date selection and date summarization, and to the previous lack of appropriate evaluation metrics for the full TLS task. In this paper, we compare different TLS strategies using appropriate evaluation frameworks, and propose a simple and effective combination of methods that improves over the state-of-the-art on all tested benchmarks. For a more robust evaluation, we also present a new TLS dataset, which is larger and spans longer time periods than previous datasets.