About
I'm a post doctoral researcher at the University of Oxford and at the Alan Turing Institute: I work on benchmarking Language Models with Prof. Michael Wooldridge and Prof. Nigel Shadbolt. I completed a Ph.D. at the same institution: my journey started in 2019 and ended in 2023. I have been lucky to be supervised by Prof. Marta Kwiatkowska. During my Ph.D. I worked on robustness as a property intersecting Natural Language Processing (NLP), computational linguistics, and linguistics. If you desire to know what I discovered during my Ph.D., is that (I hold the opinion that) robustness as formulated by the machine learning community is ill-posed for language. You can contact me via email (for anything, really). If you are interested, you can also download my resume; Scroll through this page and click the download button :) Here's a list of publications I contributed to.
News
- Mar. 2025: our paper Code Simulation as a Proxy for High-order Tasks in Large Language Models is available online.
- Mar. 2025: our paper Understanding the Logical Capabilities of Large Language Models via Out-of-Context Representation Learning is available online.
- Mar. 2025: our paper When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits is available online.
- Jan. 2025: our paper Language Models are Implicitly Continuous has been accepted at ICLR'25.
- Jan. 2025: our paper Jailbreaking Large Language Models in Infinitely Many Ways is available online.
- Dec. 2024: our paper Language Models as a Service: Overview of a New Paradigm and it its Challenges will be presented at AAAI'25 (oral and poster).
- Oct. 2024: our paper One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks is available online.
- Oct. 2024: our paper A Scalable Communication Protocol for Networks of Large Language Models is available online.
- Sept. 2024: our paper A Notion of Complexity for Theory of Mind via Discrete World Models has been accepted at EMNLP'24 (findings).
- May 2024: our paper Language Models as a Service: Overview of a New Paradigm and it its Challenges has been accepted at JAIR.
- May 2024: our paper Graph-enhanced Large Language Models in Asynchronous Plan Reasoning has been accepted at ICML'24.
- Apr. 2024: our paper Deep Neural Networks via Complex Network Theory: a Perspective has been accepted at IJCAI'24.
- Nov. 2023: I successfully defended my PhD thesis.
- Nov. 2023: our paper Language Tokenizers Introduce Unfairness Between Languages has been accepted at NeurIPS'23.
Contact Me
Oxford, UK
Email: {name}.{surname}[at]cs.ox.ac.uk. My surname is what comes after Emanuele and does not contain blank spaces.
Email: PGP <-- Use it for private enquiries.