# Frequency Effects on Syntactic Rule Learning in Transformers

arXiv: https://arxiv.org/abs/2109.07020 · HTML: https://mlsanity.com/paper/2109.07020/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 62 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [COGS: A Compositional Generalization Challenge Based on Semantic Interpretation](https://mlsanity.com/paper/2010.05465/) (2020)
- [Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/1808.09031/) (2018)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Assessing BERT's Syntactic Abilities](https://mlsanity.com/paper/1901.05287/) (2019)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [Syntactic Structure from Deep Learning](https://mlsanity.com/paper/2004.10827/) (2020)
- [Addressing "Documentation Debt" in Machine Learning Research: A Retrospective Datasheet for BookCorpus](https://mlsanity.com/paper/2105.05241/) (2021)
- [Can neural networks understand monotonicity reasoning?](https://mlsanity.com/paper/1906.06448/) (2019)
- [Refining Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/2104.09635/) (2021)
- [Small and Practical BERT Models for Sequence Labeling](https://mlsanity.com/paper/1909.00100/) (2019)
- [Probing Linguistic Systematicity](https://mlsanity.com/paper/2005.04315/) (2020)

## Built on by (most cited first, 30 of 59)

- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Impact of Pretraining Term Frequencies on Few-Shot Reasoning](https://mlsanity.com/paper/2202.07206/) (2022)
- [How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN](https://mlsanity.com/paper/2111.09509/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [Mutual Information Alleviates Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2210.13210/) (2022)
- [Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs](https://mlsanity.com/paper/2403.19827/) (2024)
- [Probing for the Usage of Grammatical Number](https://mlsanity.com/paper/2204.08831/) (2022)
- [Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions](https://mlsanity.com/paper/2207.14251/) (2022)
- [Grammatical Error Correction: A Survey of the State of the Art](https://mlsanity.com/paper/2211.05166/) (2022)
- [The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative](https://mlsanity.com/paper/2210.13181/) (2022)
- [Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability](https://mlsanity.com/paper/2308.15419/) (2023)
- [Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence](https://mlsanity.com/paper/2405.15750/) (2024)
- [Dissociating language and thought in large language models](https://mlsanity.com/paper/2301.06627/) (2023)
- [Neural reality of argument structure constructions](https://mlsanity.com/paper/2202.12246/) (2022)
- [How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases](https://mlsanity.com/paper/2305.19905/) (2023)
- [Impact of Co-occurrence on Factual Knowledge of Large Language Models](https://mlsanity.com/paper/2310.08256/) (2023)
- [Geographic Adaptation of Pretrained Language Models](https://mlsanity.com/paper/2203.08565/) (2022)
- [Construction Grammar Provides Unique Insight into Neural Language Models](https://mlsanity.com/paper/2302.02178/) (2023)
- [Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale](https://mlsanity.com/paper/2510.24963/) (2025)
- [On the Reliability of Large Language Models for Causal Discovery](https://mlsanity.com/paper/2407.19638/) (2024)
- [Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions](https://mlsanity.com/paper/2503.03862/) (2025)
- [Can Language Models Be Tricked by Language Illusions? Easier with Syntax, Harder with Semantics](https://mlsanity.com/paper/2311.01386/) (2023)
- [Beyond Text Compression: Evaluating Tokenizers Across Scales](https://mlsanity.com/paper/2506.03101/) (2025)
- [A systematic framework for generating novel experimental hypotheses from language models](https://mlsanity.com/paper/2408.05086/) (2024)
- [Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models](https://mlsanity.com/paper/2505.23689/) (2025)
- [Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge](https://mlsanity.com/paper/2112.08583/) (2021)
- [Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materials](https://mlsanity.com/paper/2204.11953/) (2022)
- [longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks](https://mlsanity.com/paper/2206.14729/) (2022)

## Abstract (arXiv)

Pre-trained language models perform well on a variety of linguistic tasks that require symbolic reasoning, raising the question of whether such models implicitly represent abstract symbols and rules. We investigate this question using the case study of BERT's performance on English subject-verb agreement. Unlike prior work, we train multiple instances of BERT from scratch, allowing us to perform a series of controlled interventions at pre-training time. We show that BERT often generalizes well to subject-verb pairs that never occurred in training, suggesting a degree of rule-governed behavior. We also find, however, that performance is heavily influenced by word frequency, with experiments showing that both the absolute frequency of a verb form, as well as the frequency relative to the alternate inflection, are causally implicated in the predictions BERT makes at inference time. Closer analysis of these frequency effects reveals that BERT's behavior is consistent with a system that correctly applies the SVA rule in general but struggles to overcome strong training priors and to estimate agreement features (singular vs. plural) on infrequent lexical items.