about me

Hi, I'm Nick.

Currently, I'm a postdoc researching AI code generation at Microsoft Research.

Previously, my research has spanned several areas and methodologies in natural language processing. Most notably, I have published in natural language inference (NLI), especially in tasks like question answering. For these models I have drawn from data sources such as structured knowledge (Knowledge Graphs, Entailment Graphs) and unstructured, open-domain text in natural language. I also research Language Model capabilities in textual understanding, doing systematic analyses of their factual hallucination, and I strategize mitigations.

I hold a Ph.D. from the University of Edinburgh and the Institute for Language, Cognition, and Computation. I also did my B.Sc. in Computer Science at Brown University.


Recent News:
Feb '24 I started a postdoc position with Microsoft Research, Cambridge.
Nov '23 Our paper, Smoothing Entailment Graphs with Language Models, won the "Best Paper" award at AACL 2023.
Oct '23 Our paper, Sources of Hallucination by Large Language Models on Inference Tasks, was accepted to EMNLP Findings 2023.
Oct '23 I defended my Ph.D. thesis, Inference of Natural Language Predicates in the Open Domain.
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 or find me on X/Twitter and LinkedIn.

© 2024 Nick McKenna