# Memorisation versus Generalisation in Pre-trained Language Models

arXiv: https://arxiv.org/abs/2105.00828 · HTML: https://mlsanity.com/paper/2105.00828/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [Pretrained Transformers Improve Out-of-Distribution Robustness](https://mlsanity.com/paper/2004.06100/) (2020)
- [Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks](https://mlsanity.com/paper/1903.11680/) (2019)
- [An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models](https://mlsanity.com/paper/2007.06778/) (2020)
- [CrossWeigh: Training Named Entity Tagger from Imperfect Annotations](https://mlsanity.com/paper/1909.01441/) (2019)
- [Cloze-driven Pretraining of Self-attention Networks](https://mlsanity.com/paper/1903.07785/) (2019)
- [Generalisation in Named Entity Recognition: A Quantitative Analysis](https://mlsanity.com/paper/1701.02877/) (2017)
- [Noisy Text Data: Achilles' Heel of BERT](https://mlsanity.com/paper/2003.12932/) (2020)

## Built on by (most cited first, 30 of 32)

- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment](https://mlsanity.com/paper/2312.12148/) (2023)
- [Does CLIP Bind Concepts? Probing Compositionality in Large Image Models](https://mlsanity.com/paper/2212.10537/) (2022)
- [DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks](https://mlsanity.com/paper/2309.17167/) (2023)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics](https://mlsanity.com/paper/2410.21272/) (2024)
- [How Do Large Language Models Acquire Factual Knowledge During Pretraining?](https://mlsanity.com/paper/2406.11813/) (2024)
- [Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions](https://mlsanity.com/paper/2211.12316/) (2022)
- [Understanding Transformer Memorization Recall Through Idioms](https://mlsanity.com/paper/2210.03588/) (2022)
- [How much do language models memorize?](https://mlsanity.com/paper/2505.24832/) (2025)
- [Memorization in NLP Fine-tuning Methods](https://mlsanity.com/paper/2205.12506/) (2022)
- [Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning](https://mlsanity.com/paper/2205.14704/) (2022)
- [A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing](https://mlsanity.com/paper/2210.04675/) (2022)
- [Koala: An Index for Quantifying Overlaps with Pre-training Corpora](https://mlsanity.com/paper/2303.14770/) (2023)
- [Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models](https://mlsanity.com/paper/2305.09144/) (2023)
- [Quantifying Generalization Complexity for Large Language Models](https://mlsanity.com/paper/2410.01769/) (2024)
- [Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks](https://mlsanity.com/paper/2210.12929/) (2022)
- [CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification](https://mlsanity.com/paper/2303.03628/) (2023)
- [Weaker Than You Think: A Critical Look at Weakly Supervised Learning](https://mlsanity.com/paper/2305.17442/) (2023)
- [Automatic Question-Answer Generation for Long-Tail Knowledge](https://mlsanity.com/paper/2403.01382/) (2024)
- [A Human Subject Study of Named Entity Recognition (NER) in Conversational Music Recommendation Queries](https://mlsanity.com/paper/2303.06944/) (2023)
- [On the Security Vulnerabilities of Text-to-SQL Models](https://mlsanity.com/paper/2211.15363/) (2022)
- [Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?](https://mlsanity.com/paper/2309.07804/) (2023)
- [PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models](https://mlsanity.com/paper/2305.04673/) (2023)
- [A State-Vector Framework for Dataset Effects](https://mlsanity.com/paper/2310.10955/) (2023)
- [Integrating curation into scientific publishing to train AI models](https://mlsanity.com/paper/2310.20440/) (2023)
- [NoisyAG-News: A Benchmark for Addressing Instance-Dependent Noise in Text Classification](https://mlsanity.com/paper/2407.06579/) (2024)
- [Large-scale investigation of weakly-supervised deep learning for the fine-grained semantic indexing of biomedical literature](https://mlsanity.com/paper/2301.09350/) (2023)
- [Query Suggestion for Retrieval-Augmented Generation via Dynamic In-Context Learning](https://mlsanity.com/paper/2601.08105/) (2026)

## Abstract (arXiv)

State-of-the-art pre-trained language models have been shown to memorise facts and perform well with limited amounts of training data. To gain a better understanding of how these models learn, we study their generalisation and memorisation capabilities in noisy and low-resource scenarios. We find that the training of these models is almost unaffected by label noise and that it is possible to reach near-optimal results even on extremely noisy datasets. However, our experiments also show that they mainly learn from high-frequency patterns and largely fail when tested on low-resource tasks such as few-shot learning and rare entity recognition. To mitigate such limitations, we propose an extension based on prototypical networks that improves performance in low-resource named entity recognition tasks.