# When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes

arXiv: https://arxiv.org/abs/2204.09722 · HTML: https://mlsanity.com/paper/2204.09722/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [Visualizing and Measuring the Geometry of BERT](https://mlsanity.com/paper/1906.02715/) (2019)
- [Stress Test Evaluation for Natural Language Inference](https://mlsanity.com/paper/1806.00692/) (2018)
- [CausaLM: Causal Model Explanation Through Counterfactual Language Models](https://mlsanity.com/paper/2005.13407/) (2020)
- [Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information](https://mlsanity.com/paper/1808.08079/) (2018)
- [A Tale of a Probe and a Parser](https://mlsanity.com/paper/2005.01641/) (2020)
- [What if This Modified That? Syntactic Interventions via Counterfactual Embeddings](https://mlsanity.com/paper/2105.14002/) (2021)
- [Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness](https://mlsanity.com/paper/1805.04212/) (2018)
- [Adapting by Pruning: A Case Study on BERT](https://mlsanity.com/paper/2105.03343/) (2021)

## Built on by (most cited first, 12 of 12)

- [Dissociating language and thought in large language models](https://mlsanity.com/paper/2301.06627/) (2023)
- [Probing for Incremental Parse States in Autoregressive Language Models](https://mlsanity.com/paper/2211.09748/) (2022)
- [Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks](https://mlsanity.com/paper/2407.04690/) (2024)
- [Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models](https://mlsanity.com/paper/2210.14328/) (2022)
- [Operationalising Representation in Natural Language Processing](https://mlsanity.com/paper/2306.08193/) (2023)
- [Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number](https://mlsanity.com/paper/2310.15151/) (2023)
- [Linguistic Interpretability of Transformer-based Language Models: a systematic review](https://mlsanity.com/paper/2504.08001/) (2025)
- [Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience](https://mlsanity.com/paper/2408.12664/) (2024)
- [Mini Minds: Exploring Bebeshka and Zlata Baby Models](https://mlsanity.com/paper/2311.03216/) (2023)
- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)
- [Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs](https://mlsanity.com/paper/2602.15846/) (2026)
- [Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy](https://mlsanity.com/paper/2608.27813/) (2026)

## Abstract (arXiv)

Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield "false negative" causality results: models may use representations of syntax, but probes may have learned to use redundant encodings of the same syntactic information. We demonstrate that models do encode syntactic information redundantly and introduce a new probe design that guides probes to consider all syntactic information present in embeddings. Using these probes, we find evidence for the use of syntax in models where prior methods did not, allowing us to boost model performance by injecting syntactic information into representations.