|国家预印本平台
首页|The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Adam Stein、Aaditya Naik、Neelay Velingker、Mayur Naik、Eric Wong

计算技术、计算机技术

Adam Stein,Aaditya Naik,Neelay Velingker,Mayur Naik,Eric Wong.The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models[EB/OL].(2025-05-30)[2025-06-22].https://arxiv.org/abs/2505.24874.点此复制

评论