Recent Results Towards Reasoning with LLMs

Abstract: 
In this presentation, I will go over a few recent topics towards understanding the limits of reasoning capabilities of large language models. I will start with an analysis of the hardness of problems like syllogisms when tackling them with the Transformer architecture; I will propose a metric to measure that hardness, and an approach to make it easier for LLMs to reduce such hardness. I will show that these limitations are not specific to the textual domain and also exist for other domains like visual tasks. I will then show how difficult it is to accurately measure the performance of modern reasoning models and will end with a few approaches to reduce the complexity of some reasoning problems.

Bio: 
Samy Bengio (PhD in computer science, University of Montreal, 1993) is a senior director of machine learning research at Apple since 2021 and adjunct professor at EPFL since 2024. Before that, he was a distinguished scientist at Google Research since 2007 where he was heading part of the Google Brain team, and at IDIAP in the early 2000s where he co-wrote the well-known open-source Torch machine learning library.
His research interests span many areas of machine learning such as deep architectures, representation learning, vision and language processing and more recently, reasoning.
He is action editor of the Journal of Machine Learning Research and on the board of the NeurIPS foundation. He was on the editorial board of the Machine Learning Journal, has been program chair (2017) and general chair (2018) of NeurIPS, program chair of ICLR (2015, 2016), general chair of BayLearn (2012-2015), MLMI (2004-2006), as well as NNSP (2002), and on the program committee of several international conferences such as NeurIPS, ICML, ICLR, ECML and IJCAI.