LLM Memory & RAG 相关度: 8/10

Overview of the TREC 2025 RAGTIME Track

Dawn Lawrie, Sean MacAvaney, James Mayfield, Luca Soldaini, Eugene Yang, Andrew Yates
arXiv: 2602.10024v1 发布: 2026-02-10 更新: 2026-02-10
下载 PDF arXiv 页面

AI 摘要

TREC 2025 RAGTIME 旨在评估多语言环境下报告生成的性能，涵盖多语言信息检索任务。

主要贡献

  • 创建多语言新闻文档集
  • 设计多语言报告生成任务
  • 提供基线结果和评估标准

方法论

通过多语言文档集和三种任务类型，评估参与者提交的报告生成系统性能，并提供评估结果。

原文摘要

The principal goal of the RAG TREC Instrument for Multilingual Evaluation (RAGTIME) track at TREC is to study report generation from multilingual source documents. The track has created a document collection containing Arabic, Chinese, English, and Russian news stories. RAGTIME includes three task types: Multilingual Report Generation, English Report Generation, and Multilingual Information Retrieval (MLIR). A total of 125 runs were submitted by 13 participating teams (and as baselines by the track coordinators) for three tasks. This overview describes these three tasks and presents the available results.

标签

RAG Multilingual Report Generation Information Retrieval Evaluation

arXiv 分类

cs.IR cs.CL