Dimitri COELHO MOLLO – 21 septembre 2023
Titre : Grounding in Large Language Models: lessons for building functional ontologies for AI
My aim in this talk is twofold. First, I will rehearse the arguments, in joint work with Raphaël Millière, that motivate the claim that language grounding (but not language understanding) is possible, and in some cases actual, at least in some current Large Language Models (LLMs). That does not mean, however, that the way language grounding works in LLMs is similar, let alone identical, to how grounding works in humans. Such differences open up two options: narrowing down the notion of grounding to capture only the phenomenon in humans; or pluralism about grounding, allowing the notion to extend more broadly to systems that fulfil the appropriate requirements for possessing intrinsic content. In the second part of the talk, taking LLMs as a case study, I will argue that pluralism is the most promising road, one that invites the application to AI of recent work in comparative and cognitive psychology, and especially the ongoing project of looking for appropriate ontologies to account for cognition and intelligence. Given the doubtful cognitive status of current AI systems, I will suggest that looking for explanatorily powerful functional ontologies can help us to better understand the capabilities and limitations of current AI systems, as well as potential ways forward for the field.
I am an Assistant Professor with focus in Philosophy of Artificial Intelligence at the Department of Historical, Philosophical and Religious Studies, at Umeå University, Sweden, and focus area coordinator at TAIGA (Centre for Transdisciplinary AI), for the area 'Understanding and Explaining Artificial Intelligence'. I am also an external Principal Investigator at the Science of Intelligence Cluster, in Berlin, Germany. My research focuses on foundational and epistemic questions within artificial intelligence and cognitive science, looking for ways to improve our understanding of mind, cognition, and intelligence in biological and artificial systems. My work often intersects issues in Ethics of Artificial Intelligence, Philosophy of Computing, and Philosophy of Biology.
Coelho Mollo and Millière (2023), The Vector Grounding Problem - https://arxiv.org/abs/2304.01481
Francken, Slors, Craver (2022), Cognitive ontology and the search for neural mechanisms: three foundational problems - https://link.springer.com/article/10.1007/s11229-022-03701-2