# Do Language Models Encode Knowledge of Linguistic Constraint Violations?

arXiv: https://arxiv.org/abs/2605.12055 · HTML: https://mlsanity.com/paper/2605.12055/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders](https://mlsanity.com/paper/2407.14435/) (2024)
- [Evaluating Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2310.19736/) (2023)
- [A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders](https://mlsanity.com/paper/2409.14507/) (2024)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [Learning Multi-Level Features with Matryoshka Sparse Autoencoders](https://mlsanity.com/paper/2503.17547/) (2025)
- [Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models](https://mlsanity.com/paper/2402.16438/) (2024)
- [How is BERT surprised? Layerwise detection of linguistic anomalies](https://mlsanity.com/paper/2105.07452/) (2021)
- [Unveiling Linguistic Regions in Large Language Models](https://mlsanity.com/paper/2402.14700/) (2024)
- [What Can String Probability Tell Us About Grammaticality?](https://mlsanity.com/paper/2510.16227/) (2025)
- [LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder](https://mlsanity.com/paper/2502.20344/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) achieve strong linguistic performance, yet their internal mechanisms for producing these predictions remain unclear. We investigate the hypothesis that LLMs encode representations of linguistic constraint violations within their parameters, which are selectively activated when processing ungrammatical sentences. To test this, we use sparse autoencoders to decompose polysemantic activations into sparse, monosemantic features and recover candidates for violation-related features. We introduce a sensitivity score for identifying features that are preferentially activated on constraint-violated versus well-formed inputs, enabling unsupervised detection of potential violation-specific features. We further propose a conjunctive falsification framework with three criteria evaluated jointly. Overall, the results are negative in two respects: (1) the falsification criteria are not jointly satisfied across linguistic phenomena, and (2) no features are consistently shared across all categories. While some phenomena show partial evidence of selective causal structure, the overall pattern provides limited support for a unified set of grammatical violation detectors in current LMs.