The face of Gabriel Recchia.I’m Gabriel Recchia, a cognitive scientist working on the evaluation and alignment of large language models as the director of Modulo Research. I’m proud to have contributed to the recent agenda paper Foundational challenges in assuring alignment and safety of large language models. You can read more about my current research interests under the ‘Evaluations’ and ‘Research’ tabs at See my Google Scholar profile for a list of my most cited works. 

Previously, I was at David Spiegelhalter’s Winton Centre for Risk and Evidence Communication at the University of Cambridge, where I worked on how to communicate information in ways that support comprehension and informed decision-making.

 I have spent much of my career involved in research investigating the capabilities, properties, and applications of distributional models trained on large volumes of text, and continued this while at the Winton Centre to explore their applications in characterizing how risk is communicated and perceived. I also led on user testing research and evaluation of patient-friendly genetic reports and the NHS: Predict family of prognostic tools

Before this, I was affiliated with the Centre for Research in the Arts, Social Sciences and Humanities, where I worked with distributional approaches to the analysis of large corpora of historical texts, and the University of Memphis Institute for Intelligent Systems, where I investigated what geographical information was latent in simple co-occurrence-based models.

I received my bachelor’s degree in Symbolic Systems from Stanford University in 2007, and my doctorate is in Cognitive Science at Indiana University, with a minor in computational linguistics and with language modelling as my content specialization.

I’m interested in a range of topics related to scalable oversight and evaluating the faithfulness/trustworthiness of explanations generated by language models, such as metrics and benchmarks for such evaluation, process-oriented learning, debate, sandwiching, evaluating risks and benefits of approaches driven by AI feedback, externalized reasoning oversight, and some approaches to explainable AI.