# Can recursive neural tensor networks learn logical reasoning?

arXiv: https://arxiv.org/abs/1312.6192 · HTML: https://mlsanity.com/paper/1312.6192/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2013.

## Built on by (most cited first, 4 of 4)

- [Teaching Arithmetic to Small Transformers](https://mlsanity.com/paper/2307.03381/) (2023)
- [LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models](https://mlsanity.com/paper/2408.15778/) (2024)
- [Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units](https://mlsanity.com/paper/2104.02899/) (2021)
- [Neuro-symbolic model for cantilever beams damage detection](https://mlsanity.com/paper/2305.03063/) (2023)

## Abstract (arXiv)

Recursive neural network models and their accompanying vector representations for words have seen success in an array of increasingly semantically sophisticated tasks, but almost nothing is known about their ability to accurately capture the aspects of linguistic meaning that are necessary for interpretation or reasoning. To evaluate this, I train a recursive model on a new corpus of constructed examples of logical reasoning in short sentences, like the inference of "some animal walks" from "some dog walks" or "some cat walks," given that dogs and cats are animals. This model learns representations that generalize well to new types of reasoning pattern in all but a few cases, a result which is promising for the ability of learned representation models to capture logical reasoning.