# Revisiting k-NN for Fine-tuning Pre-trained Language Models

arXiv: https://arxiv.org/abs/2304.09058 · HTML: https://mlsanity.com/paper/2304.09058/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 18 Apr 2023.

## Builds on (most cited first, 23 of 23)

- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2010.00710/) (2020)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [Text Classification Algorithms: A Survey](https://mlsanity.com/paper/1904.08067/) (2019)
- [Reasoning with Latent Structure Refinement for Document-Level Relation Extraction](https://mlsanity.com/paper/2005.06312/) (2020)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [Efficient Nearest Neighbor Language Models](https://mlsanity.com/paper/2109.04212/) (2021)
- [Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval](https://mlsanity.com/paper/2201.12431/) (2022)
- [BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA](https://mlsanity.com/paper/2005.00766/) (2020)
- [GNN-LM: Language Modeling based on Global Contexts via GNN](https://mlsanity.com/paper/2110.08743/) (2021)
- [kNN-Prompt: Nearest Neighbor Zero-Shot Inference](https://mlsanity.com/paper/2205.13792/) (2022)
- [A Simple Cache Model for Image Recognition](https://mlsanity.com/paper/1805.08709/) (2018)
- [Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings](https://mlsanity.com/paper/2201.05575/) (2022)
- [KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier](https://mlsanity.com/paper/2110.02523/) (2021)

## Abstract (arXiv)

Pre-trained Language Models (PLMs), as parametric-based eager learners, have become the de-facto choice for current paradigms of Natural Language Processing (NLP). In contrast, k-Nearest-Neighbor (kNN) classifiers, as the lazy learning paradigm, tend to mitigate over-fitting and isolated noise. In this paper, we revisit kNN classifiers for augmenting the PLMs-based classifiers. From the methodological level, we propose to adopt kNN with textual representations of PLMs in two steps: (1) Utilize kNN as prior knowledge to calibrate the training process. (2) Linearly interpolate the probability distribution predicted by kNN with that of the PLMs' classifier. At the heart of our approach is the implementation of kNN-calibrated training, which treats predicted results as indicators for easy versus hard examples during the training process. From the perspective of the diversity of application scenarios, we conduct extensive experiments on fine-tuning, prompt-tuning paradigms and zero-shot, few-shot and fully-supervised settings, respectively, across eight diverse end-tasks. We hope our exploration will encourage the community to revisit the power of classical methods for efficient NLP. Code and datasets are available in https://github.com/zjunlp/Revisit-KNN.