The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Stein, Adam, Naik, Aaditya, Velingker, Neelay, Naik, Mayur, Wong, Eric
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915314035326976
author Stein, Adam
Naik, Aaditya
Velingker, Neelay
Naik, Mayur
Wong, Eric
author_facet Stein, Adam
Naik, Aaditya
Velingker, Neelay
Naik, Mayur
Wong, Eric
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24874
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
Stein, Adam
Naik, Aaditya
Velingker, Neelay
Naik, Mayur
Wong, Eric
Machine Learning
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.
title The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
topic Machine Learning
url https://arxiv.org/abs/2505.24874