Pinzhen Chen

2022-2023, Zhanghao Hu, Yijun Yang, and Junjie Xu, Machine Learning Practical.
- Efficient question answering, shortlisted for the best project prize sponsored by IBM UK and published at LREC-COLING'24 [paper].
2024-2025, Dayyán O'Brien, Research Assistant.
- Language code and data processing, as part of the continued pre-training effort for EMMA-500 [paper].
- DocHPLT: Massively multilingual document-level translation data provision [paper].
- Disentangling LLM memorization and reasoning in mathematics.
2025, Kriti Gupta, MSc Thesis.
- Exposing knowledge leakage in distillation: Evidence from question answering and translation.
2025, Andrés Cotton, MSc Thesis, with Alexandra Birch.
- Finding the right place: Evaluating AI agents in open-ended multi-participant venue selection.
2025, Beatriz Gavilan, MSc Thesis, with Alexandra Birch.
- Experiential learning in the finance domain.

Informatics Research Proposal (INFR11147): tutor and marker, 2020/21, 2024/25
Machine Learning Practical (INFR11132): mentor and marker, 2020/21, 2021/22, 2022/23
Natural Language Understanding, Generation, and Machine Translation (INFR11157): lab demonstrator, 2021/22
Introductory Applied Machine Learning (INFR11182): marker, 2020/21, 2021/22
Foundations of Natural Language Processing (INFR09028): lab demonstrator and marker, 2018/19
System Design Project (INFR09032): mentor, 2018/19
Reasoning and Agents (INFR08010): lab demonstrator, 2017/18
Processing Formal and Natural Languages (INFR08008): lab demonstrator, 2017/18