# Teaching Syntax by Adversarial Distraction

arXiv: https://arxiv.org/abs/1810.11067 · HTML: https://mlsanity.com/paper/1810.11067/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2018.

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

- [Linear Connectivity Reveals Generalization Strategies](https://mlsanity.com/paper/2205.12411/) (2022)
- [Fast Few-shot Debugging for NLU Test Suites](https://mlsanity.com/paper/2204.06555/) (2022)
- [Can current NLI systems handle German word order? Investigating language model performance on a new German challenge set of minimal pairs](https://mlsanity.com/paper/2306.04523/) (2023)
- [Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing](https://mlsanity.com/paper/2607.20115/) (2026)

## Abstract (arXiv)

Existing entailment datasets mainly pose problems which can be answered without attention to grammar or word order. Learning syntax requires comparing examples where different grammar and word order change the desired classification. We introduce several datasets based on synthetic transformations of natural entailment examples in SNLI or FEVER, to teach aspects of grammar and word order. We show that without retraining, popular entailment models are unaware that these syntactic differences change meaning. With retraining, some but not all popular entailment models can learn to compare the syntax properly.