# The Domain Mixed Unit: A New Neural Arithmetic Layer

arXiv: https://arxiv.org/abs/2509.08180 · HTML: https://mlsanity.com/paper/2509.08180/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 8 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 6 of 6)

- [Llemma: An Open Language Model For Mathematics](https://mlsanity.com/paper/2310.10631/) (2023)
- [Neural Arithmetic Logic Units](https://mlsanity.com/paper/1808.00508/) (2018)
- [Neural Arithmetic Units](https://mlsanity.com/paper/2001.05016/) (2020)
- [On Evaluating the Generalization of LSTM Models in Formal Languages](https://mlsanity.com/paper/1811.01001/) (2018)
- [A Primer for Neural Arithmetic Logic Modules](https://mlsanity.com/paper/2101.09530/) (2021)
- [Measuring Arithmetic Extrapolation Performance](https://mlsanity.com/paper/1910.01888/) (2019)

## Abstract (arXiv)

The Domain Mixed Unit (DMU) is a new neural arithmetic unit that learns a single parameter gate that mixes between log-space and linear-space representations while performing either addition (DMU add) or subtraction (DMU sub). Two initializations are proposed for the DMU: one covering addition and multiplication, and another covering subtraction and division. The DMU achieves state-of-the-art performance on the NALM Benchmark, a dataset designed to test the ability of neural arithmetic units to generalize arithmetic operations, specifically performing with the highest percentage solved over all seeds on multiplication and division. The DMU will be submitted as a pull request to the open-source NALM benchmark, and its code is available on GitHub at https://github.com/marict/nalm-benchmark