Yingjia Wan

Student Researcher in Natural Language Processing

Language Technology Lab, University of Cambridge

About

Hi! I am Yingjia. I studied NLP at the Language Technology lab, University of Cambridge, as an MPhil student supervised by Prof Ivan Vulić. I am passionable about a wide range of NLP topics that I have been working on, including Large Language Model (LLM) Reasoning (in multiple domains), LLM Hallucination & Fact-Checking, Debiasing, Multimodality, and Cognition-Inspired NLP.

I grow from a interdisplinary background of humanties and computer science: I studied linguistics and neuroscience at University of Macau where I graduated top of the cohort as an undergraduate valedictorian.

I am currently looking for intern and PhD opportunities in NLP (and always open for collaboration). Feel free to drop me an email (yingjiawan.alisa[AT]gmail.com) if you are interested in working with me or just a chat!

Interests

Model Reasoning
Model Hallucination & Fact-Checking
Automated Theorem Proving
Multimodality
Cognition-Inspired NLP

Education

M.Phil. in Theoretical & Applied Linguistics (NLP track), 2022-2023
University of Cambridge
Funded Exchange, 2019-2020
University of Michigan
B.A. in English Studies, 2017-2021
University of Macau

Recent Publications

Zhongshen Zeng, Yinhong Liu, Yingjia Wan, Jingyao Li, Pengguang Chen, Jianbo Dai, Yuxuan Yao, Rongwu Xu, Zehan Qi, Wanru Zhao, Linling Shen, Jianqiao Lu, Haochen Tan, Yukang Chen, Hao Zhang, Zhan Shi, Bailin Wang, Zhijiang Guo, Jiaya Jia (2024). Mr.Ben: A Comprehensive Meta-Reasoning Benchmark for Analyzing Large Language Models. Preprint available on arXiv:2406.13975..

Code Dataset Blog arXiv

Jianqing Lu, Zhengying Liu, Yingjia Wan, Yinya Huang, Haiming Wang, Zhicheng Yang, Jing Tang, Zhijiang Guo (2024). Process-Driven Autoformalization in Lean 4. Preprint available at arXiv:2406.01940..

Code Dataset arxiv

Jianqing Lu, Zhiyang Dou, Hongru Wang, Zeyu Cao, Jianbo Dai, Yingjia Wan, Yinya Huang, Zhijiang Guo (2024). AutoCV: Empowering Reasoning with Automated Process Labeling via Confidence Variation. Preprint available at arXiv:2405.16802..

Code arxiv

Jianqing Lu, Yingjia Wan, Yinya Huang, Zhengying Liu, Zhijiang Guo (2024). AUTOALIGN: Automated Alignment Evaluation in Autoformalization. Preprint provided upon request.

Yingjia Wan, Ivan Vulić (2023). Multimodal Prompt Tuning for Cognition-Enhanced NLP. [MPhil Dissertation].

PDF Code

See all publications