LLMs predict content expiration for Baidu web search

Researchers have developed a new framework using Large Language Models (LLMs) to predict content expiration in web search, addressing the challenge of information freshness. This approach, deployed in Baidu search, reformulates timeliness as a dynamic validity inference task. By extracting temporal contexts and using LLMs to determine a query-specific "validity horizon," the system aims to provide more relevant and up-to-date search results, showing significant improvements in user experience metrics. AI

影响 Enhances web search relevance by using LLMs to dynamically assess information timeliness, improving user experience.

排序理由 The cluster contains an academic paper detailing a new framework and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

• Baidu
• Large Language Models
• LLMs

• 论文
• 产品
• 基础设施

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →