Hi, I'm Nick.
I'm an applied researcher working on GitHub Copilot. I work on the contextualization team, improving editor completions by supplying smart context. Previously, I was a research scientist in code generation at Microsoft Research.
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 student-teacher approaches for improving code-gen in low-resource programming languages; for extended copilot dialogues leveraging code for computation and verification; 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 rich, semantic modeling.
I hold a Ph.D. from the University of Edinburgh and the Institute for Language, Cognition, and Computation, where I was advised by Mark Steedman. I also hold a B.Sc. in Computer Science from Brown University.
Recent News:
| Apr '25 | I started as an applied researcher at 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 started as a research scientist at Microsoft Research, Cambridge. |
| Nov '23 | Our paper, Smoothing Entailment Graphs with Language Models, won the "Best Paper" award at AACL 2023. |