Hi, I'm Nick.
I'm an applied researcher working on GitHub Copilot. I work on model contextualization, supplying smart context to improve models in static and agentic modes. Previously, I was a research scientist in code generation at Microsoft Research.
I hold a Ph.D. in Natural Language Processing from the University of Edinburgh School of Informatics, where I was advised by Mark Steedman. I also hold a B.Sc. in Computer Science from Brown University.
Research Interests
I am broadly interested in Language Model capabilities in textual understanding, coding, and tool use, and mitigating LLM hallucinations. I pursue models which draw on external, human-editable data sources such as structured knowledge and open-domain text, using tools and code to accomplish tasks precisely. In code generation, I have investigated various approaches for improving program synthesis in low-resource programming languages; for LLM dialogues which are verified by code generation and execution; and for accomplishing complex data science tasks. In NLP, I have worked extensively in natural language inference (NLI), especially for tasks like question answering, summarization, and Knowledge Graph usage through lexical semantic modeling.
Recent News
| Apr '25 | I joined GitHub Applied Sciences, working on Copilot. |
| Dec '24 | Our paper, Evaluating the Evaluator: Measuring LLMs' adherence to Task Evaluation Instructions, was accepted to AAAI 2025. |
| Feb '24 | I joined Microsoft Research, Cambridge. |
| Nov '23 | Our paper, Smoothing Entailment Graphs with Language Models, won the "Best Paper" award at AACL 2023. |