# Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance

arXiv: https://arxiv.org/abs/2412.17408 · HTML: https://mlsanity.com/paper/2412.17408/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 10 of 10)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Self-Evaluation Guided Beam Search for Reasoning](https://mlsanity.com/paper/2305.00633/) (2023)
- [Examining the State-of-the-Art in News Timeline Summarization](https://mlsanity.com/paper/2005.10107/) (2020)
- [A Temporally Sensitive Submodularity Framework for Timeline Summarization](https://mlsanity.com/paper/1810.07949/) (2018)
- [TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale](https://mlsanity.com/paper/2403.10351/) (2024)
- [LMGQS: A Large-scale Dataset for Query-focused Summarization](https://mlsanity.com/paper/2305.13086/) (2023)
- [IDEAL: Leveraging Infinite and Dynamic Characterizations of Large Language Models for Query-focused Summarization](https://mlsanity.com/paper/2407.10486/) (2024)

## Built on by (most cited first, 7 of 7)

- [SlideTailor: Personalized Presentation Slide Generation for Scientific Papers](https://mlsanity.com/paper/2512.20292/) (2025)
- [KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions](https://mlsanity.com/paper/2601.04745/) (2026)
- [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)
- [Leveraging Generative Models for Real-Time Query-Driven Text Summarization in Large-Scale Web Search](https://mlsanity.com/paper/2508.20559/) (2025)
- [PledgeTracker: A System for Monitoring the Fulfilment of Pledges](https://mlsanity.com/paper/2509.11804/) (2025)
- [NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning](https://mlsanity.com/paper/2606.13171/) (2026)

## Abstract (arXiv)

Given news articles about an entity, such as a public figure or organization, timeline summarization (TLS) involves generating a timeline that summarizes the key events about the entity. However, the TLS task is too underspecified, since what is of interest to each reader may vary, and hence there is not a single ideal or optimal timeline. In this paper, we introduce a novel task, called Constrained Timeline Summarization (CTLS), where a timeline is generated in which all events in the timeline meet some constraint. An example of a constrained timeline concerns the legal battles of Tiger Woods, where only events related to his legal problems are selected to appear in the timeline. We collected a new human-verified dataset of constrained timelines involving 47 entities and 5 constraints per entity. We propose an approach that employs a large language model (LLM) to summarize news articles according to a specified constraint and cluster them to identify key events to include in a constrained timeline. In addition, we propose a novel self-reflection method during summary generation, demonstrating that this approach successfully leads to improved performance.