# RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search

arXiv: https://arxiv.org/abs/2605.13052 · HTML: https://mlsanity.com/paper/2605.13052/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 14 of 14)

- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [LightThinker: Thinking Step-by-Step Compression](https://mlsanity.com/paper/2502.15589/) (2025)
- [Sufficient Context: A New Lens on Retrieval Augmented Generation Systems](https://mlsanity.com/paper/2411.06037/) (2024)
- [ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning](https://mlsanity.com/paper/2012.15283/) (2020)
- [Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?](https://mlsanity.com/paper/2406.09072/) (2024)
- [TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions](https://mlsanity.com/paper/2502.21024/) (2025)
- [Large Language Models are Contrastive Reasoners](https://mlsanity.com/paper/2403.08211/) (2024)
- [Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering](https://mlsanity.com/paper/2409.16909/) (2024)
- [Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs](https://mlsanity.com/paper/2502.12462/) (2025)
- [LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning](https://mlsanity.com/paper/2502.14644/) (2025)
- [Recency Ranking by Diversification of Result Set](https://mlsanity.com/paper/2401.14595/) (2024)
- [Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives](https://mlsanity.com/paper/2410.05558/) (2024)
- [Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search](https://mlsanity.com/paper/2503.21098/) (2025)

## Built on by (most cited first, 1 of 1)

- [Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search](https://mlsanity.com/paper/2605.27066/) (2026)

## Abstract (arXiv)

In commercial web search, aligning content freshness with user intent remains challenging due to the highly varied lifespans of information. Traditional industrial approaches rely on static time-window filtering, resulting in "one-size-fits-all" rankings where content may be chronologically recent but semantically expired. To address the limitation, we present a novel Large Language Models (LLMs)-based Query-Aware Dynamic Content Expiration Prediction Framework deployed in Baidu search, reformulating timeliness as a dynamic validity inference task. Our framework extracts fine-grained temporal contexts from documents and leverages LLMs to deduce a query-specific "validity horizon"-a semantic boundary defining when information becomes obsolete based on user intent. Integrated with robust hallucination mitigation strategies to ensure reliability, our approach has been evaluated through offline and online A/B testing on live production traffic. Results demonstrate significant improvements in search freshness and user experience metrics, validating the effectiveness of LLM-driven reasoning for solving semantic expiration at an industrial scale.