Overview of the TREC 2025 RAGTIME Track
🤖 AI Summary
This study addresses the challenge of multilingual automated report generation by systematically integrating multilingual information retrieval and report generation within the TREC framework for the first time. The project constructed a news document collection covering Arabic, Chinese, English, and Russian, and established three tasks: multilingual report generation, English-only report generation, and multilingual retrieval, attracting 13 participating teams with 125 system runs. By leveraging multilingual retrieval, cross-lingual text processing, and natural language generation techniques, this work establishes a standardized evaluation benchmark for the field and provides a comprehensive comparative analysis of system performance, thereby advancing research and development in cross-lingual automated report generation.
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
Multilingual Report Generation
Information Retrieval
Multilingual Evaluation
Document Collection
TREC
Innovation
Methods, ideas, or system contributions that make the work stand out.
Retrieval-Augmented Generation
Multilingual Report Generation
Multilingual Information Retrieval
TREC RAGTIME
Cross-lingual Evaluation
🔎 Similar Papers
No similar papers found.
