Greetings! I am Yunze Song, currently pursuing my graduate studies at the National University of Singapore. My research is centered on advancing the field of artificial intelligence, with a particular emphasis on the fair evaluation of large models and the safer development of generative AI systems. Additionally, I am exploring the integration of large language models into robotics, aiming to enhance the capabilities of AI-driven systems in practical applications.

I have had the opportunity to conduct research at esteemed institutions such as Peking University and Westlake University, where my work focused on LLM Evaluation and Retrieval-Augmented Generation. I aspire to achieve meaningful outcomes through research and develop the capacity to bring happiness and positive impact to others.

😎 News

2024.02: I joined The Knowledge Computing Lab at Peking University as a research intern, supervised by Dr. Yidong Wang and Prof. Wei Ye.
2023.09: I completed a research internship at Text Intelligence Lab of Westlake University, supervised by Dr. Linyi Yang and Prof. Yue Zhang.
2023.07: I received my first-class honors bachelor’s degree with top-ranking distinction, under the supervision of Prof. Limin Yu.

📝 Publications

EMNLP 2024 System Demonstration Track (Oral)

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation Paper Code

Xuanwang Zhang *,Yunze Song *, Yidong Wang, Shuyun Tang, Xinfeng Li, Zhengran Zeng, Zhen Wu, Wei Ye, Wenyuan Xu, Yue Zhang, Xinyu Dai, Shikun Zhang, Qingsong Wen

Two major obstacles hinder RAG’s progress. First, there is a growing lack of thorough and fair comparisons between emerging RAG algorithms. Second, open-source tools like LlamaIndex and LangChain use high-level abstractions, reducing transparency and limiting innovation in algorithm development and evaluation. To bridge this gap, we introduce RAGLAB, a modular, research-focused open-source library. RAGLAB replicates six existing algorithms and offers a comprehensive ecosystem for exploring RAG techniques. Using RAGLAB, we fairly compare six RAG algorithms across ten benchmarks, enabling researchers to efficiently evaluate and develop new algorithms.

🎖 Honors and Awards

2019-2020: University Academic Achievement Award (5,000 CNY)
2020-2021 & 2021-2022: University Academic Excellence Award (10,000 CNY Per Year)
2020-2021 & 2021-2022: University Outstanding Students Award

📖 Educations

2025.01 - 2026.07, Master of Science in Robotics at National University of Singapore.
2019.09 - 2023.07, Undergraduate student in the Department of Computer Science and Technology at Xi’an Jiaotong-Liverpool University in China and the University of Liverpool in the UK.

💻 Internships

2023.11 - now: Research Intern, Peking University
2023.09 - 2024.02: NLP Engineer, FaceMind Co., Ltd. (An AI Startup)
2023.05 - 2023.09: Research Intern, Westlake University
2022.06 - 2022.09: Research Assistant, Xi’an Jiaotong-Liverpool University

📷 Photography