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

• URL: http://arxiv.org/abs/2605.27066v1
• Date: Tue, 26 May 2026 14:16:27 GMT
• Title: Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search
• Abstract summary: We present QDET (Query-Driven Event Timeline Summarization), a production system deployed on Baidu Search.<n>QDET identifies and organizes sub-events closely relevant to the query from noisy candidate sets formed by millions of documents retrieved daily.<n>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.
• Score: 49.02761046363752
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring [2.6996154332513895]
  We investigate task-aware fine-tuning of LLaMA-3.1-8B for AES using parameter-efficient LoRA with 4-bit quantization.<n>We compare three training curricula: (i) Sequential fine-tuning on lead, then position, then claim, then evidence, then conclusion, (ii) Independent (task-specific models), and (iii) Randomized.
  arXiv  Detail & Related papers  (2026-06-09T02:23:46Z)
• ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking [2.2573512203799626]
  We propose ReacTOD, a bounded neuro-symbolic architecture that reformulates NLU as discrete tool calls within a self-correcting ReAct loop governed by deterministic validation.<n>A bounded ReAct loop enables iterative self-correction, improving accuracy by up to 9.3 percentage points over single-pass inference on MultiWOZ.
  arXiv  Detail & Related papers  (2026-05-18T20:06:04Z)
• When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models [13.891522069967507]
  We introduce ReaLM-Retrieve, a reasoning-aware retrieval framework.<n>Step-level uncertainty detector identifies knowledge gaps at reasoning-step rather than token or sentence level.<n>Retrieval intervention policy learns when external evidence maximally benefits ongoing reasoning.
  arXiv  Detail & Related papers  (2026-04-29T13:15:44Z)
• TSAQA: Time Series Analysis Question And Answering Benchmark [85.35545785252309]
  Time series data are integral to critical applications across domains such as finance, healthcare, transportation, and environmental science.<n>We introduce TSAQA, a novel unified benchmark designed to broaden task coverage and evaluate diverse temporal analysis capabilities.
  arXiv  Detail & Related papers  (2026-01-30T17:28:56Z)
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents [80.33280979339123]
  We introduce Memory-T1, a framework that learns a time-aware memory selection policy using reinforcement learning (RL)<n>On the Time-Dialog benchmark, Memory-T1 boosts a 7B model to an overall score of 67.0%, establishing a new state-of-the-art performance for open-source models.
  arXiv  Detail & Related papers  (2025-12-23T06:37:29Z)
• Robust Driving QA through Metadata-Grounded Context and Task-Specific Prompts [27.64955941993406]
  We present a vision-language QA system for autonomous driving that answers high-level perception, prediction, and planning questions.<n>In experiments on a driving QA benchmark, our approach significantly outperforms the baseline Qwen2.5 models.<n> Notably, the system maintains 96% accuracy under severe visual corruption.
  arXiv  Detail & Related papers  (2025-10-21T18:24:59Z)
• HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy [61.668591984635846]
  HAMLET is a framework to adapt Vision-Language-Action models to attend to the historical context during action prediction.<n>We show that HAMLET successfully transforms a state-of-the-art VLA into a history-aware policy.<n>On top of GR00T N1.5, HAMLET achieves an average success rate of 76.4% on history-dependent real-world tasks.
  arXiv  Detail & Related papers  (2025-10-01T09:15:52Z)
• TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models [105.47481207029047]
  We introduce Time Series Reasoning Suite (TSR-Suite), which formalizes four atomic tasks that span three fundamental capabilities for reasoning with time series.<n>We also introduce Time Omni-1, the first unified reasoning model designed to address diverse real-world problems demanding time series reasoning.
  arXiv  Detail & Related papers  (2025-09-29T13:54:34Z)
• TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions [18.87473448633352]
  We propose TempRetriever, which explicitly incorporates temporal information by embedding both the query date and document timestamp into the retrieval process.<n> TempRetriever achieves a 6.63% improvement in Top-1 retrieval accuracy and a 3.79% improvement in NDCG@10 compared to the standard DPR on ArchivalQA.<n>We also propose a novel, time-based negative sampling strategy which further enhances retrieval performance by addressing temporal misalignment during training.
  arXiv  Detail & Related papers  (2025-02-28T13:06:25Z)
• Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines [83.65380507372483]
  Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box. This paper shows how to leverage recent advances in NLP and multi-modal learning to augment a pre-trained model with search engine retrieval.
  arXiv  Detail & Related papers  (2023-11-29T05:33:28Z)
• MOTOR: A Time-To-Event Foundation Model For Structured Medical Records [4.773344142823636]
  We present a self-supervised, time-to-event (TTE) foundation model called MOTOR (Many Outcome Time Oriented Representations) TTE models are used for estimating the probability distribution of the time until a specific event occurs. Motor addresses this challenge by pretraining on up to 55M patient records (9B clinical events)
  arXiv  Detail & Related papers  (2023-01-09T02:42:39Z)

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.