# Do we need Label Regularization to Fine-tune Pre-trained Language Models?

arXiv: https://arxiv.org/abs/2205.12428 · HTML: https://mlsanity.com/paper/2205.12428/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 25 May 2022.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 31)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Accounting for Variance in Machine Learning Benchmarks](https://mlsanity.com/paper/2103.03098/) (2021)
- [An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models](https://mlsanity.com/paper/2007.06778/) (2020)
- [PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation](https://mlsanity.com/paper/2104.12369/) (2021)
- [Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures](https://mlsanity.com/paper/2007.08970/) (2020)
- [ALP-KD: Attention-Based Layer Projection for Knowledge Distillation](https://mlsanity.com/paper/2012.14022/) (2020)
- [Annealing Knowledge Distillation](https://mlsanity.com/paper/2104.07163/) (2021)
- [Contrastive Distillation on Intermediate Representations for Language Model Compression](https://mlsanity.com/paper/2009.14167/) (2020)
- [Transferring Inductive Biases through Knowledge Distillation](https://mlsanity.com/paper/2006.00555/) (2020)
- [The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks](https://mlsanity.com/paper/2006.01005/) (2020)
- [MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation](https://mlsanity.com/paper/2105.05912/) (2021)
- [Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers](https://mlsanity.com/paper/2010.03034/) (2020)
- [KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation](https://mlsanity.com/paper/2109.06243/) (2021)

## Built on by (most cited first, 2 of 2)

- [Alternating Training-based Label Smoothing Enhances Prompt Generalization](https://mlsanity.com/paper/2508.17846/) (2025)
- [LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization](https://mlsanity.com/paper/2305.04971/) (2023)

## Abstract (arXiv)

Knowledge Distillation (KD) is a prominent neural model compression technique that heavily relies on teacher network predictions to guide the training of a student model. Considering the ever-growing size of pre-trained language models (PLMs), KD is often adopted in many NLP tasks involving PLMs. However, it is evident that in KD, deploying the teacher network during training adds to the memory and computational requirements of training. In the computer vision literature, the necessity of the teacher network is put under scrutiny by showing that KD is a label regularization technique that can be replaced with lighter teacher-free variants such as the label-smoothing technique. However, to the best of our knowledge, this issue is not investigated in NLP. Therefore, this work concerns studying different label regularization techniques and whether we actually need them to improve the fine-tuning of smaller PLM networks on downstream tasks. In this regard, we did a comprehensive set of experiments on different PLMs such as BERT, RoBERTa, and GPT with more than 600 distinct trials and ran each configuration five times. This investigation led to a surprising observation that KD and other label regularization techniques do not play any meaningful role over regular fine-tuning when the student model is pre-trained. We further explore this phenomenon in different settings of NLP and computer vision tasks and demonstrate that pre-training itself acts as a kind of regularization, and additional label regularization is unnecessary.