# Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search

arXiv: https://arxiv.org/abs/2605.27066 · HTML: https://mlsanity.com/paper/2605.27066/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 18 of 18)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2101.12631/) (2021)
- [Examining the State-of-the-Art in News Timeline Summarization](https://mlsanity.com/paper/2005.10107/) (2020)
- [Time-R1: Towards Comprehensive Temporal Reasoning in LLMs](https://mlsanity.com/paper/2505.13508/) (2025)
- [SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression](https://mlsanity.com/paper/2007.08954/) (2020)
- [A Temporally Sensitive Submodularity Framework for Timeline Summarization](https://mlsanity.com/paper/1810.07949/) (2018)
- [Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization](https://mlsanity.com/paper/2501.00888/) (2025)
- [Unsupervised Key Event Detection from Massive Text Corpora](https://mlsanity.com/paper/2206.04153/) (2022)
- [CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization](https://mlsanity.com/paper/2210.14190/) (2022)
- [Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order](https://mlsanity.com/paper/2301.00867/) (2023)
- [Forecasting the Buzz: Enriching Hashtag Popularity Prediction with LLM Reasoning](https://mlsanity.com/paper/2510.08481/) (2025)
- [RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search](https://mlsanity.com/paper/2605.13052/) (2026)

## Abstract (arXiv)

Understanding how events evolve over time is essential for search engines handling queries about trending news. We present QDET (Query-Driven Event Timeline Summarization), a production system deployed on Baidu Search that constructs focused event timelines to explain specific query events. Unlike traditional topic-centric approaches that aim for comprehensive coverage, QDET identifies and organizes sub-events closely relevant to the query from noisy candidate sets formed by millions of documents retrieved daily. QDET incorporates two key innovations: (1) multi-task supervised fine-tuning with three auxiliary tasks-temporal ordering, causal judgment, and timeline completion-that enable compact models to match the performance of much larger general-purpose models in specialized domains; (2) reinforcement learning-based event concise summarization that enforces strict length constraints while maintaining semantic quality, achieving 88.2% length compliance and outperforming 671B-scale models by 7.7 points in constraint satisfaction. Our fine-tuned 7B parameter model achieves 76.2% F1 score on timeline summarization, slightly surpassing the zero-shot performance of DeepSeek-R1-671B (76.1% F1) while using only 1% of its parameters-demonstrating that domain-specific optimization enables production-ready models with comparable quality at drastically reduced computational costs. Online A/B tests on Baidu Search validate real-world effectiveness, showing 5.5% CTR improvement, 4.6% longer dwell time, and 4.4% deeper exploration compared to single-task baselines. We further demonstrate that timeline understanding transfers to heat prediction, confirming effective knowledge transfer to downstream tasks.