Youze

Youze “Hargen” Zheng[pron.]

Data Science & Mathematics-Computer Science
University of California, San Diego
Email: yoz018 [at] ucsd [dot] edu

Scholar LinkedIn GitHub CV

I'm an undergraduate student at the University of California, San Diego with a broad interest in artificial intelligence, machine learning, and natural language processing (NLP). Currently, I'm a research assistant in the Laboratory for Emerging Intelligence, advised by Dr. Leon Bergen and Dr. Ramamohan Paturi.

My research focuses on advancing understanding of cutting-edge large language models and developing novel methods to improve their capabilities. Previously, I have worked on building efficient long-context retrievers at sentence level [1] and contributed to developing a biomedical benchmark to evaluate model performance and identify critical gaps in current systems [2].

I plan to pursue graduate studies in Computer Science in the areas of machine learning and NLP.

News

Publications

Below is a list of my published papers. You may also see my Google Scholar page.

SPS paper thumbnail
Single-Pass Document Scanning for Question Answering
Weili Cao*, Jianyou Wang*, Youze Zheng*, Longtian Bao*, Qirui Zheng, Taylor Berg-Kirkpatrick, Ramamohan Paturi, Leon Bergen
COLM 2025. Oral Spotlight Presentation (top 5%)
TL;DR Paper Code Citation
TL;DR: Single-pass scanner in long document QA outperforms embedding methods while nearly matching full-context LLMs at much lower cost.
@inproceedings{cao2025singlepass,
    title={Single-Pass Document Scanning for Question Answering},
    author={Weili Cao and Jianyou Wang and Youze Zheng and Longtian Bao and Qirui Zheng and Taylor Berg-Kirkpatrick and Ramamohan Paturi and Leon Bergen},
    booktitle={Second Conference on Language Modeling},
    year={2025}}
RoBBR paper thumbnail
Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark
Jianyou Wang*, Weili Cao*, Longtian Bao, Youze Zheng, Gil Pasternak, Kaicheng Wang, Xiaoyue Wang, Ramamohan Paturi, Leon Bergen
EMNLP 2025.
TL;DR Paper Code Citation
TL;DR: A Biomedical Risk-of-Bias Benchmark created with novel subtasks that measure retrieval and reasoning abilities of LLMs and embedding models when performing risk-of-bias assessment.
@inproceedings{wang2025measuring,
    title={Measuring Risk of Bias in Biomedical Reports: The Ro{BBR} Benchmark},
    author={Jianyou Wang and Weili Cao and Longtian Bao and Youze Zheng and Gil Pasternak and Kaicheng Wang and Xiaoyue Wang and Ramamohan Paturi and Leon Bergen},
    booktitle={The 2025 Conference on Empirical Methods in Natural Language Processing},
    year={2025}}

*Equal Contribution.

Teaching Experiences

Below is a complete list of courses that I have served as a teaching assistant at UC San Diego.