about me

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.
selected publications

Nick McKenna*, Tianyi Li*, Liang Cheng, Mohammad Javad Hosseini, Mark Johnson, and Mark Steedman. Sources of Hallucination by Large Language Models on Inference Tasks. Findings of EMNLP, 2023. Paper Link.

Nick McKenna, Tianyi Li, Mark Johnson, and Mark Steedman. Smoothing Entailment Graphs with Language Models. AACL, 2023. *Best Paper Award!* Paper Link.

Nick McKenna, Liane Guillou, Mohammad Javad Hosseini, Sander Bijl de Vroe, Mark Johnson, and Mark Steedman. Multivalent Entailment Graphs for Question Answering. EMNLP, 2021. Paper Link.


For a full list of publications, refer to my CV.

contact

Reach me by email.

© 2025 Nick McKenna