Lorenzo Pacchiardi

Research Associate, University of Cambridge
New paper: How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
I am a Research Associate at the Leverhulme Centre for the Future of Intelligence at the University of Cambridge, where I develop a framework for evaluating the cognitive capabilities of Large Language Models, together with Prof José Hernández-Orallo and Dr Lucy Cheke.
I previously worked on detecting lying in large language models with Dr Owain Evans and on technical standards for AI for the EU AI Act at the Future of Life Institute. I am deeply interested in AI policy (particularly at the EU level).
I obtained a PhD in Statistics and Machine Learning at Oxford, during which I worked on Bayesian simulation-based inference, generative models and probabilistic forecasting (with applications to meteorology). My supervisors were Prof. Ritabrata Dutta (Uni. Warwick) and Prof. Geoff Nicholls (Uni. Oxford).
Before my PhD studies, I obtained a Bachelor’s degree in Physical Engineering from Politecnico di Torino (Italy) and an MSc in Physics of Complex Systems from Politecnico di Torino and Université Paris-Sud, France. I carried out my MSc thesis at LightOn, a machine learning startup in Paris.
news
Aug 1, 2023 |
I am happy to communicate that I will join the Leverhulme Centre for the Future of Intelligence at the University of Cambridge in October 2023 ![]() |
---|---|
Jul 15, 2023 |
Today, I formally graduated from my PhD at Oxford! ![]() |
Dec 20, 2022 | I won a travel award at the International Conference for Statistics and Data Science by the Institute of Mathematical Statistics. I really enjoyed the opportunity to present my work there! |
Nov 17, 2022 |
On the 9th of November, I successfully defended my PhD thesis ![]() |
Jun 3, 2022 |
I have two preprints on arXiv exploring an alternative to adversarial training to train generative networks; the first applies it to probabilistic forecasting, while the second is concerned with Likelihood-Free Inference. I feel that is a promising overlooked approach. Happy to hear any feedback! ![]() |