# Compositional Language Understanding with Text-based Relational Reasoning

arXiv: https://arxiv.org/abs/1811.02959 · HTML: https://mlsanity.com/paper/1811.02959/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2018.

## Built on by (most cited first, 3 of 3)

- [Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models](https://mlsanity.com/paper/2402.14848/) (2024)
- [Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning](https://mlsanity.com/paper/2501.07845/) (2025)
- [Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios](https://mlsanity.com/paper/2502.19973/) (2025)

## Abstract (arXiv)

Neural networks for natural language reasoning have largely focused on extractive, fact-based question-answering (QA) and common-sense inference. However, it is also crucial to understand the extent to which neural networks can perform relational reasoning and combinatorial generalization from natural language---abilities that are often obscured by annotation artifacts and the dominance of language modeling in standard QA benchmarks. In this work, we present a novel benchmark dataset for language understanding that isolates performance on relational reasoning. We also present a neural message-passing baseline and show that this model, which incorporates a relational inductive bias, is superior at combinatorial generalization compared to a traditional recurrent neural network approach.