# Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning

arXiv: https://arxiv.org/abs/2404.14607 · HTML: https://mlsanity.com/paper/2404.14607/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 55 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 30 of 41)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (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)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning](https://mlsanity.com/paper/2207.12819/) (2022)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)

## Built on by (most cited first, 9 of 9)

- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization](https://mlsanity.com/paper/2502.04295/) (2025)
- [Continual Learning for Generative AI: From LLMs to MLLMs and Beyond](https://mlsanity.com/paper/2506.13045/) (2025)
- [Continual Learning Using Only Large Language Model Prompting](https://mlsanity.com/paper/2412.15479/) (2024)
- [Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning](https://mlsanity.com/paper/2606.01379/) (2026)
- [GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning](https://mlsanity.com/paper/2507.14725/) (2025)
- [Revealing Microscopic Objects in Fluorescence Live Imaging by Video-to-video Translation Based on A Spatial-temporal Generative Adversarial Network](https://mlsanity.com/paper/2502.16342/) (2025)
- [Information-Theoretic Complementary Prompts for Improved Continual Text Classification](https://mlsanity.com/paper/2505.20933/) (2025)
- [Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts](https://mlsanity.com/paper/2609.39365/) (2026)

## Abstract (arXiv)

This paper introduces Q-tuning, a novel approach for continual prompt tuning that enables the lifelong learning of a pre-trained language model. When learning a new task, Q-tuning trains a task-specific prompt by adding it to a prompt queue consisting of the prompts from older tasks. To better transfer the knowledge of old tasks, we design an adaptive knowledge aggregation technique that reweighs previous prompts in the queue with a learnable low-rank matrix. Once the prompt queue reaches its maximum capacity, we leverage a PCA-based eviction rule to reduce the queue's size, allowing the newly trained prompt to be added while preserving the primary knowledge of old tasks. In order to mitigate the accumulation of information loss caused by the eviction, we additionally propose a globally shared prefix prompt and a memory retention regularization based on information theory. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods substantially on continual prompt tuning benchmarks. Moreover, our approach enables lifelong learning on linearly growing task sequences while requiring constant complexity for training and inference.