English

A Neural Rewriting System to Solve Algorithmic Problems

Neural and Evolutionary Computing 2024-07-15 v2 Artificial Intelligence Computation and Language

Abstract

Modern neural network architectures still struggle to learn algorithmic procedures that require to systematically apply compositional rules to solve out-of-distribution problem instances. In this work, we focus on formula simplification problems, a class of synthetic benchmarks used to study the systematic generalization capabilities of neural architectures. We propose a modular architecture designed to learn a general procedure for solving nested mathematical formulas by only relying on a minimal set of training examples. Inspired by rewriting systems, a classic framework in symbolic artificial intelligence, we include in the architecture three specialized and interacting modules: the Selector, trained to identify solvable sub-expressions; the Solver, mapping sub-expressions to their values; and the Combiner, replacing sub-expressions in the original formula with the solution provided by the Solver. We benchmark our system against the Neural Data Router, a recent model specialized for systematic generalization, and a state-of-the-art large language model (GPT-4) probed with advanced prompting strategies. We demonstrate that our approach achieves a higher degree of out-of-distribution generalization compared to these alternative approaches on three different types of formula simplification problems, and we discuss its limitations by analyzing its failures.

Keywords

Cite

@article{arxiv.2402.17407,
  title  = {A Neural Rewriting System to Solve Algorithmic Problems},
  author = {Flavio Petruzzellis and Alberto Testolin and Alessandro Sperduti},
  journal= {arXiv preprint arXiv:2402.17407},
  year   = {2024}
}

Comments

Updated version (v2) accepted at the 27th European Conference on Artificial Intelligence (ECAI 24)

R2 v1 2026-06-28T15:01:46.559Z