Adrian de Wynter

I am a principal applied scientist at Microsoft and a researcher (PGR) at the University of York. I work in projects related to natural language understanding/generation and fundamental problems in AI, such as reasoning and formal modelling of dialogue, like LLMs.

At Microsoft my work involves leading, designing, and deploying Word- and Office- AI features and research. These deal with composition (what you see when you type in Word), multilinguality (e.g., expanding products to new markets), measurement (reasoning, automated evaluation), personalisation, and other workstreams. Yes, I also work on buzzwords like 'agentic workflows'. Most of the work here, you can see it in Word Copilot.

My primary research interest is reasoning as it relates to language in humans and machines. Lately I have focused on LLM-based reasoning capabilities (e.g. here, here, and here). My theoretical work is intuitionistic: algorithms have guarantees of complexity and convergence via constructive proofs, and must relate to a realistic (e.g. production) scenario. This gives meaningful answers about complex problems.

For example, we used category theory to prove that some prompting strategies are objectively better than others; and that they would produce more preferrable outcomes by users (and ended up being a product in Word). I also recently wrote an algorithm with cryptographic guarantees for determining trust in LLMs-as-judges.

In earlier work I showed that finding a globally optimal solution to model compression is undecidable, but proved that polynomial-time approximation algorithms exist--and applied these results to BERT and reaching a (then) state-of-the-art on model compression. This last contribution was later adapted for quantum circuit optimisation in work at ORNL. I also showed (bridging learning theory and topological data analysis) how (and when) LLM-based data augmentation works.

My other research interests relate to recreational mathematics (games), preserving endangered languages, and computational social science. In the latter I have worked on mitigating toxicity, unfairness, and other harms of LLMs; research on LLM research; and worked on the first study of the impact of ChatGPT on loneliness. And I also publish in SIGBOVIK, because this job is actually fun.

I have served as reviewer for AAAI, EMNLP, and so on. I also review for Nature (Communications, Artificial Intelligence), IEEE Transactions on Games, ACM TIST; and I am now on Twitter.

Last updated: August '25.