LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers

1 code implementation • 23 Oct 2023 • Theo X. Olausson, Alex Gu, Benjamin Lipkin, Cedegao E. Zhang, Armando Solar-Lezama, Joshua B. Tenenbaum, Roger Levy

Logical reasoning, i. e., deductively inferring the truth value of a conclusion from a set of premises, is an important task for artificial intelligence with wide potential impacts on science, mathematics, and society.

GPT-3.5 GPT-4 +1

AI for Mathematics: A Cognitive Science Perspective

no code implementations • 19 Oct 2023 • Cedegao E. Zhang, Katherine M. Collins, Adrian Weller, Joshua B. Tenenbaum

Mathematics is one of the most powerful conceptual systems developed and used by the human species.

The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs

no code implementations • 25 Jun 2023 • Lance Ying, Katherine M. Collins, Megan Wei, Cedegao E. Zhang, Tan Zhi-Xuan, Adrian Weller, Joshua B. Tenenbaum, Lionel Wong

To test our model, we design and run a human experiment on a linguistic goal inference task.

Language Modelling Large Language Model