# Does Episodic Memory Help Close the Lexical Frequency Gap in Sensitivity to Syntactic Contrasts? A Test Using Retrieval-Augmented Language Models

arXiv: https://arxiv.org/abs/2608.23851 · HTML: https://mlsanity.com/paper/2608.23851/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

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

- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining](https://mlsanity.com/paper/2305.10429/) (2023)
- [Should You Mask 15% in Masked Language Modeling?](https://mlsanity.com/paper/2202.08005/) (2022)
- [Efficient Nearest Neighbor Language Models](https://mlsanity.com/paper/2109.04212/) (2021)
- [Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2504.08165/) (2025)
- [Frequency Effects on Syntactic Rule Learning in Transformers](https://mlsanity.com/paper/2109.07020/) (2021)
- [Transformers generalize differently from information stored in context vs in weights](https://mlsanity.com/paper/2210.05675/) (2022)
- [Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2412.05149/) (2024)
- [Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models](https://mlsanity.com/paper/2212.10769/) (2022)
- [You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM](https://mlsanity.com/paper/2210.15859/) (2022)
- [Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences](https://mlsanity.com/paper/2509.16189/) (2025)
- [Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing](https://mlsanity.com/paper/2410.11462/) (2024)
- [FairyTailor: A Multimodal Generative Framework for Storytelling](https://mlsanity.com/paper/2108.04324/) (2021)
- [Long-Tail Crisis in Nearest Neighbor Language Models](https://mlsanity.com/paper/2503.22426/) (2025)

## Abstract (arXiv)

Grammatical knowledge and how it is empirically tested are typically considered robust to the frequency of the lexical items in the expressions. However, neural network-based models of grammaticality exhibit high sensitivity to lexical frequency. We draw upon Complementary Learning Systems theory to test the hypothesis that robustness to lexical frequency can arise via a hippocampal episodic memory mechanism, which enables rapid encoding and retrieval of specific experiences and allows learners to leverage them when processing rare patterns. We use retrieval-augmented language models as an instantiation of such an episodic memory mechanism (specifically, k-nearest-neighbor language models that augment parametric models with explicit instance storage), and test whether this augmentation helps close the lexical frequency gap that vanilla language models exhibit in syntactic contrast tests. Using syntactic contrasts with frequency-stratified test items, we find that retrieval augmentation narrows the performance gap between high- and low-frequency items, consistent with episodic memory compensating for weak parametric representations. This benefit is consistent across different syntactic phenomena and across models pretrained on child-realistic and large-scale data. Additionally, we show that structural information is critical for effective retrieval, whereas semantic similarity alone provides little benefit. While these are promising proof-of-concept results supporting our hypothesis, the frequency gap is narrowed rather than fully closed. Based on our analyses, we propose preferential reweighting of retrieved instances, better representations and retrieval strategies for structural information, and flexible configurations of storage and retrieval as promising future directions for improving the implementation of episodic memory in language models.