# Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization

arXiv: https://arxiv.org/abs/2305.03937 · HTML: https://mlsanity.com/paper/2305.03937/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 6 May 2023.

## Builds on (most cited first, 29 of 29)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [A Convergence Theory for Deep Learning via Over-Parameterization](https://mlsanity.com/paper/1811.03962/) (2018)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer](https://mlsanity.com/paper/2110.07904/) (2021)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension](https://mlsanity.com/paper/1810.12885/) (2018)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)

## Built on by (most cited first, 30 of 64)

- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [LoRA-GA: Low-Rank Adaptation with Gradient Approximation](https://mlsanity.com/paper/2407.05000/) (2024)
- [CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2406.05223/) (2024)
- [SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation](https://mlsanity.com/paper/2501.01765/) (2025)
- [InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding](https://mlsanity.com/paper/2306.04933/) (2023)
- [Prompting Language-Informed Distribution for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.14428/) (2023)
- [Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling](https://mlsanity.com/paper/2310.12100/) (2023)
- [Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics](https://mlsanity.com/paper/2505.23194/) (2025)
- [Position: Editing Large Language Models Poses Serious Safety Risks](https://mlsanity.com/paper/2502.02958/) (2025)
- [A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness](https://mlsanity.com/paper/2312.01082/) (2023)
- [Extending Whisper with prompt tuning to target-speaker ASR](https://mlsanity.com/paper/2312.08079/) (2023)
- [See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition](https://mlsanity.com/paper/2407.05417/) (2024)
- [Propulsion: Steering LLM with Tiny Fine-Tuning](https://mlsanity.com/paper/2409.10927/) (2024)
- [PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning](https://mlsanity.com/paper/2407.02211/) (2024)
- [MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba](https://mlsanity.com/paper/2411.03855/) (2024)
- [Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning](https://mlsanity.com/paper/2410.08598/) (2024)
- [EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference](https://mlsanity.com/paper/2502.04700/) (2025)
- [Advancing Prompt-Based Methods for Replay-Independent General Continual Learning](https://mlsanity.com/paper/2503.00677/) (2025)
- [A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space](https://mlsanity.com/paper/2510.14301/) (2025)
- [Decomposed Prompt Tuning via Low-Rank Reparameterization](https://mlsanity.com/paper/2310.10094/) (2023)
- [All You Need is One: Capsule Prompt Tuning with a Single Vector](https://mlsanity.com/paper/2510.16670/) (2025)
- [Soft Prompt Tuning for Cross-Lingual Transfer: When Less is More](https://mlsanity.com/paper/2402.03782/) (2024)
- [A Survey on Prompt Tuning](https://mlsanity.com/paper/2507.06085/) (2025)
- [Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation](https://mlsanity.com/paper/2501.15377/) (2025)
- [RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts](https://mlsanity.com/paper/2502.03044/) (2025)
- [PaCA: Partial Connection Adaptation for Efficient Fine-Tuning](https://mlsanity.com/paper/2503.01905/) (2025)
- [PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning](https://mlsanity.com/paper/2505.09519/) (2025)
- [Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation](https://mlsanity.com/paper/2510.23123/) (2025)
- [Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning](https://mlsanity.com/paper/2405.14739/) (2024)
- [The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models](https://mlsanity.com/paper/2410.16672/) (2024)

## Abstract (arXiv)

Prompt tuning is one of the successful approaches for parameter-efficient tuning of pre-trained language models. Despite being arguably the most parameter-efficient (tuned soft prompts constitute <0.1% of total parameters), it typically performs worse than other efficient tuning methods and is quite sensitive to hyper-parameters. In this work, we introduce Residual Prompt Tuning - a simple and efficient method that significantly improves the performance and stability of prompt tuning. We propose to reparameterize soft prompt embeddings using a shallow network with a residual connection. Our experiments show that Residual Prompt Tuning significantly outperforms prompt tuning on SuperGLUE benchmark. Notably, our method reaches +7 points improvement over prompt tuning with T5-Base and allows to reduce the prompt length by 10x without hurting performance. In addition, we show that our approach is robust to the choice of learning rate and prompt initialization, and is effective in few-shot settings.