AnonyRAG is a question-answering dataset for entity anonymization tasks released by Tencent Youtu Lab, Monash University and Hong Kong Polytechnic University in 2025. The related paper results are "Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning", which aims to evaluate whether the retrieval-augmented generation (RAG) system relies on retrieval to obtain evidence when entities are anonymized. This dataset is drawn from four classic novels: Water Margin, Dream of the Red Chamber, Moby-Dick, and Middlemarch. It covers both question-answer pairs and text snippets, and is available in both Chinese and English. The question-answer portion contains approximately 1,397 questions, including general questions and answers, multiple-choice questions, and entity anonymization recovery tasks, with questions categorized as simple and complex. The text portion provides text paragraphs as retrieval corpus to support question-answering tasks. It is suitable for RAG model evaluation, complex multi-hop reasoning research, knowledge question-answering system development, and entity anonymization and recovery tasks.

Citation

@misc{dong2025youtugraphragverticallyunifiedagents,
title={Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning},
author={Junnan Dong and Siyu An and Yifei Yu and Qian-Wen Zhang and Linhao Luo and Xiao Huang and Yunsheng Wu and Di Yin and Xing Sun},
year={2025},
eprint={2508.19855},
archivePrefix={arXiv},
primaryClass={cs.IR},
url={https://arxiv.org/abs/2508.19855},
}