no code implementations • 25 Jul 2023 • Tomohiro Sawada, Daniel Paleka, Alexander Havrilla, Pranav Tadepalli, Paula Vidas, Alexander Kranias, John J. Nay, Kshitij Gupta, Aran Komatsuzaki
As a subset of ARB, we introduce a challenging set of math and physics problems which require advanced symbolic reasoning and domain knowledge.
no code implementations • 12 Jun 2023 • John J. Nay, David Karamardian, Sarah B. Lawsky, WenTing Tao, Meghana Bhat, Raghav Jain, Aaron Travis Lee, Jonathan H. Choi, Jungo Kasai
Better understanding of Large Language Models' (LLMs) legal analysis abilities can contribute to improving the efficiency of legal services, governing artificial intelligence, and leveraging LLMs to identify inconsistencies in law.
no code implementations • 24 Jan 2023 • John J. Nay
Through an empirical study on thousands of evaluation labels we constructed from U. S. court opinions, we demonstrate that large language models (LLMs) are beginning to exhibit an "understanding" of one of the most relevant legal standards for AI agents: fiduciary obligations.
1 code implementation • 3 Jan 2023 • John J. Nay
We use hundreds of novel ground-truth labels of the relevance of a bill to a company to benchmark the performance of the model.
no code implementations • 14 Sep 2022 • John J. Nay
We are currently unable to specify human goals and societal values in a way that reliably directs AI behavior.
no code implementations • WS 2016 • John J. Nay
We also learn representations for more fine-grained word sources: individual Presidents and (2-year) Congresses.
no code implementations • 7 Jul 2016 • John J. Nay
To test the relative importance of text and context, we compared the text model to a context-only model that uses variables such as whether the bill's sponsor is in the majority party.
1 code implementation • 29 Mar 2016 • John J. Nay, Martin Van der Linden, Jonathan M. Gilligan
We conduct sensitivity analyses to determine how a variety of factors describing both the market and the physical climate may affect traders' beliefs about the cause of global climate change.
Multiagent Systems Physics and Society Economics
1 code implementation • 26 Mar 2016 • John J. Nay, Jonathan M. Gilligan
This article outlines a method for automatically generating models of dynamic decision-making that both have strong predictive power and are interpretable in human terms.