Papers › A Primer for Neural Arithmetic Logic Modules

A Primer for Neural Arithmetic Logic Modules

23 Jan 2021arXiv:2101.09530archive 2025-07-28

Bhumika Mistry, Katayoun Farrahi, Jonathon Hare

Neural Arithmetic Logic Modules have become a growing area of interest, though remain a niche field. These modules are neural networks which aim to achieve systematic generalisation in learning arithmetic and/or logic operations such as {+, -, ×, ÷, ≤, AND} while also being interpretable. This paper is the first in discussing the current state of progress of this field, explaining key works, starting with the Neural Arithmetic Logic Unit (NALU). Focusing on the shortcomings of the NALU, we provide an in-depth analysis to reason about design choices of recent modules. A cross-comparison between modules is made on experiment setups and findings, where we highlight inconsistencies in a fundamental experiment causing the inability to directly compare across papers. To alleviate the existing inconsistencies, we create a benchmark which compares all existing arithmetic NALMs. We finish by providing a novel discussion of existing applications for NALU and research directions requiring further exploration.

PaperPDFCode

Code

bmistry4/nalm-benchmark officialmentioned in paperpytorchMIT report
bmistry4/nalu-stable-exp-neurips-review mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections