The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
Stein, Adam, Naik, Aaditya, Velingker, Neelay, Naik, Mayur, Wong, Eric
–arXiv.org Artificial Intelligence
Neuro-symbolic learning was proposed to address challenges with training neural networks for complex reasoning tasks with the added benefits of interpretability, reliability, and efficiency. Neuro-symbolic learning methods traditionally train neural models in conjunction with symbolic programs, but they face significant challenges that limit them to simplistic problems. On the other hand, purely-neural foundation models now reach state-of-the-art performance through prompting rather than training, but they are often unreliable and lack interpretability. Supplementing foundation models with symbolic programs, which we call neuro-symbolic prompting, provides a way to use these models for complex reasoning tasks. Doing so raises the question: What role does specialized model training as part of neuro-symbolic learning have in the age of foundation models? To explore this question, we highlight three pitfalls of traditional neuro-symbolic learning with respect to the compute, data, and programs leading to generalization problems. This position paper argues that foundation models enable generalizable neuro-symbolic solutions, offering a path towards achieving the original goals of neuro-symbolic learning without the downsides of training from scratch.
arXiv.org Artificial Intelligence
Jun-2-2025
- Country:
- Asia
- Europe > United Kingdom
- England > Greater London > London (0.04)
- North America > United States
- Pennsylvania (0.05)
- Oceania > Australia
- Genre:
- Research Report (1.00)
- Industry:
- Education (0.93)
- Technology: