When no paths lead to Rome: Benchmarking systematic neural relational reasoning

Das, Anirban, Khalid, Muhammad Irtaza, Peñaloza, Rafael and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2025. When no paths lead to Rome: Benchmarking systematic neural relational reasoning. Presented at: 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA, USA and Mexico City, Mexico, 2-7 December 2025. Advances in Neural Information Processing Systems 38. NeurIPS, pp. 17245-17284. 10.52202/085713-0518

PDF - Published Version Download (1MB)

Abstract

Designing models that can learn to reason in a systematic way is an important and long-standing challenge. In recent years, a wide range of solutions have been proposed for the specific case of systematic relational reasoning, including Neuro- Symbolic approaches, variants of the Transformer architecture, and specialised Graph Neural Networks. However, existing benchmarks for systematic relational reasoning focus on an overly simplified setting, based on the assumption that reasoning can be reduced to composing relational paths. In fact, this assumption is hard-baked into the architecture of several recent models, leading to approaches that can perform well on existing benchmarks but are difficult to generalise to other settings. To support further progress in the field of systematic relational reasoning with neural networks, we introduce NoRA, a new benchmark which adds several levels of difficulty and requires models to go beyond path-based reasoning.

Item Type:	Conference or Workshop Item - published (Paper)
Status:	Published
Schools:	Schools > Computational & Mathematical Sciences
Publisher:	NeurIPS
Date of First Compliant Deposit:	17 August 2026
Last Modified:	17 Aug 2026 13:45
URI:	https://orca.cardiff.ac.uk/id/eprint/189037

Actions (repository staff only)

Edit Item