# Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner

arXiv: https://arxiv.org/abs/2305.01711 · HTML: https://mlsanity.com/paper/2305.01711/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 73 of its 108 references that are in the map.
- First posted on arXiv 2 May 2023.

## Builds on (most cited first, 30 of 73)

- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)

## Built on by (most cited first, 23 of 23)

- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Instruction Tuning With Loss Over Instructions](https://mlsanity.com/paper/2405.14394/) (2024)
- [DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2309.05173/) (2023)
- [Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models](https://mlsanity.com/paper/2408.02085/) (2024)
- [Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation](https://mlsanity.com/paper/2402.18334/) (2024)
- [Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines](https://mlsanity.com/paper/2502.16377/) (2025)
- [Rethinking Semi-supervised Learning with Language Models](https://mlsanity.com/paper/2305.13002/) (2023)
- [Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding](https://mlsanity.com/paper/2307.07880/) (2023)
- [Understanding Likelihood Over-optimisation in Direct Alignment Algorithms](https://mlsanity.com/paper/2410.11677/) (2024)
- [SGPT: Few-Shot Prompt Tuning for Signed Graphs](https://mlsanity.com/paper/2412.12155/) (2024)
- [When and What to Ask Through World States and Text Instructions: IGLU NLP Challenge Solution](https://mlsanity.com/paper/2305.05754/) (2023)
- [Self Contrastive Learning for Session-based Recommendation](https://mlsanity.com/paper/2306.01266/) (2023)
- [Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis](https://mlsanity.com/paper/2306.07664/) (2023)
- [Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE](https://mlsanity.com/paper/2505.23868/) (2025)
- [TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining](https://mlsanity.com/paper/2410.10006/) (2024)
- [An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts](https://mlsanity.com/paper/2501.12521/) (2025)
- [Solving Dialogue Grounding Embodied Task in a Simulated Environment using Further Masked Language Modeling](https://mlsanity.com/paper/2306.12387/) (2023)
- [Lexical Entrainment for Conversational Systems](https://mlsanity.com/paper/2310.09651/) (2023)
- [Improving Agent Interactions in Virtual Environments with Language Models](https://mlsanity.com/paper/2402.05440/) (2024)
- [A Comparative Study of Pre-training and Self-training](https://mlsanity.com/paper/2409.02751/) (2024)
- [Repository-Level Solidity Code Generation with Large Language Models: From Prompting to Fine-Tuning](https://mlsanity.com/paper/2606.19988/) (2026)
- [Reading the News: Adapting Large Language Models to Swedish Journalism Through Continued Pre-Training](https://mlsanity.com/paper/2608.30609/) (2026)

## Abstract (arXiv)

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on task-related texts improves the performance of fine-tuning (FT) in downstream tasks. Through experiments on eight single-sentence tasks and eight sentence-pair tasks in both semi-supervised and fully-supervised settings, we find that conventional continued pre-training does not consistently provide benefits and can even be detrimental for sentence-pair tasks or when prompt-based FT is used. To tackle these issues, we propose Prompt-based Continued Pre-training (PCP), which combines the idea of instruction tuning with conventional continued pre-training. Our approach aims to improve the performance of prompt-based FT by presenting both task-related texts and prompt templates to LMs through unsupervised pre-training objectives before fine-tuning for the target task. Our empirical evaluations on 21 benchmarks demonstrate that the PCP consistently improves the performance of state-of-the-art prompt-based FT approaches (up to 20.1% absolute) in both semi-supervised and fully-supervised settings, even with only hundreds of unlabelled examples. Additionally, prompt-based FT with the PCP outperforms state-of-the-art semi-supervised approaches with greater simplicity, eliminating the need for an iterative process and extra data augmentation. Our further analysis explores the performance lower bound of the PCP and reveals that the advantages of PCP persist across different sizes of models and datasets.