# Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory

arXiv: https://arxiv.org/abs/2303.01421 · HTML: https://mlsanity.com/paper/2303.01421/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 27 of 27)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2010.00710/) (2020)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)
- [Towards Continual Knowledge Learning of Language Models](https://mlsanity.com/paper/2110.03215/) (2021)
- [Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting](https://mlsanity.com/paper/2004.12651/) (2020)
- [LAMOL: LAnguage MOdeling for Lifelong Language Learning](https://mlsanity.com/paper/1909.03329/) (2019)
- [Fine-tuned Language Models are Continual Learners](https://mlsanity.com/paper/2205.12393/) (2022)
- [Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora](https://mlsanity.com/paper/2110.08534/) (2021)
- [Efficient Nearest Neighbor Language Models](https://mlsanity.com/paper/2109.04212/) (2021)
- [Adaptive Semiparametric Language Models](https://mlsanity.com/paper/2102.02557/) (2021)
- [ELLE: Efficient Lifelong Pre-training for Emerging Data](https://mlsanity.com/paper/2203.06311/) (2022)
- [Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale](https://mlsanity.com/paper/2212.09095/) (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)
- [Adaptation Approaches for Nearest Neighbor Language Models](https://mlsanity.com/paper/2211.07828/) (2022)
- [Nearest Neighbor Language Models for Stylistic Controllable Generation](https://mlsanity.com/paper/2210.15762/) (2022)

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

- [In-context Autoencoder for Context Compression in a Large Language Model](https://mlsanity.com/paper/2307.06945/) (2023)
- [How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances](https://mlsanity.com/paper/2310.07343/) (2023)
- [Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation](https://mlsanity.com/paper/2310.15746/) (2023)
- [Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models](https://mlsanity.com/paper/2310.07589/) (2023)
- [Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models](https://mlsanity.com/paper/2312.07887/) (2023)
- [Pre-training Limited Memory Language Models with Internal and External Knowledge](https://mlsanity.com/paper/2505.15962/) (2025)
- [Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion](https://mlsanity.com/paper/2502.12598/) (2025)
- [Collaborative Evolving Strategy for Automatic Data-Centric Development](https://mlsanity.com/paper/2407.18690/) (2024)
- [A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models](https://mlsanity.com/paper/2410.04103/) (2024)
- [Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation](https://mlsanity.com/paper/2602.14469/) (2026)
- [Heterogenous Memory Augmented Neural Networks](https://mlsanity.com/paper/2310.10909/) (2023)
- [Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction](https://mlsanity.com/paper/2606.15416/) (2026)

## Abstract (arXiv)

Semiparametric language models (LMs) have shown promise in various Natural Language Processing (NLP) tasks. However, they utilize non-parametric memory as static storage, which lacks learning capability and remains disconnected from the internal information flow of the parametric models, limiting scalability and efficiency. Based on recent interpretability theories of LMs, we reconceptualize the non-parametric memory represented by kNN-LM as a learnable Mixture-of-Neighbors Induction Memory (MoNIM), which synergizes the induction capabilities of attention heads with the memorization strength of feed-forward networks (FFN). By integrating into the model's information flow, MoNIM functions as an FFN-like bypass layer within the Transformer architecture, enabling effective learning of new knowledge. Extensive experiments demonstrate that MoNIM is a retentive and scalable continual learner in both data- and model-wise, enhancing the scalability and continual learning performance of semiparametric LMs.