Biography
Diana Robinson is a visiting researcher with the ML@CL group. She completed her PhD in computer science at the University of Cambridge in 2025, specialising in human-computer interaction. Her focus was on interaction design of clinical decision support tools, looking at ways of representing and working with uncertainty in this context. Diana was also a Student Fellow at the Leverhulme Centre for the Future of Intelligence where she was previously a research assistant exploring ethical questions relating to AI in applications ranging from immigration to medicine.
Diana was a Visiting Scholar at the MIT Media Lab in the Opera of the Future group in 2017, working on the Philadelphia City Symphony. Prior to that, she worked as a Commodity Risk Analyst in BP’s Integrated Supply and Trading business. She was a Princeton Project 55 Fellow in 2012/13.
Diana holds an MBA from the Cambridge Judge Business School and a BA in philosophy from Princeton University.
Links
Recent Publications
Prompt Variability Effects on LLM Code Generation
Third International Workshop on Large Language Models for Code (LLM4Code 2026), co-located with ICSE 2026, :
LLM Performance for Code Generation on Noisy Tasks
:
The Human Visual System Can Inspire New Interaction Paradigms for LLMs
:
Requirements are All You Need: The Final Frontier for End-User Software Engineering
ACM Transactions on Software Engineering and Methodology, :
Investigating Uncertainty in Postoperative Bleeding Management: Design Principles for Decision Support
Proceedings of the 35th International BCS Human-Computer Interaction Conference (HCI2022), :