# Teaching Neural Module Networks to Do Arithmetic

arXiv: https://arxiv.org/abs/2210.02703 · HTML: https://mlsanity.com/paper/2210.02703/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 6 Oct 2022.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [Injecting Numerical Reasoning Skills into Language Models](https://mlsanity.com/paper/2004.04487/) (2020)
- [Neural Module Networks for Reasoning over Text](https://mlsanity.com/paper/1912.04971/) (2019)
- [NumNet: Machine Reading Comprehension with Numerical Reasoning](https://mlsanity.com/paper/1910.06701/) (2019)
- [Question Directed Graph Attention Network for Numerical Reasoning over Text](https://mlsanity.com/paper/2009.07448/) (2020)
- [Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning](https://mlsanity.com/paper/2101.11802/) (2021)
- [Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text](https://mlsanity.com/paper/2109.02289/) (2021)

## Built on by (most cited first, 1 of 1)

- [FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning](https://mlsanity.com/paper/2402.12692/) (2024)

## Abstract (arXiv)

Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks(NMNs), follow the programmer-interpreter framework and design trainable modules to learn different reasoning skills. However, NMNs only have limited reasoning abilities, and lack numerical reasoning capability. We up-grade NMNs by: (a) bridging the gap between its interpreter and the complex questions; (b) introducing addition and subtraction modules that perform numerical reasoning over numbers. On a subset of DROP, experimental results show that our proposed methods enhance NMNs' numerical reasoning skills by 17.7% improvement of F1 score and significantly outperform previous state-of-the-art models.