# Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?

arXiv: https://arxiv.org/abs/2302.08143 · HTML: https://mlsanity.com/paper/2302.08143/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 115 of its 179 references that are in the map.
- First posted on arXiv 16 Feb 2023.

## Builds on (most cited first, 30 of 115)

- [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)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (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)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [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)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)

## Built on by (most cited first, 11 of 11)

- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [Robust Prompt Optimization for Large Language Models Against Distribution Shifts](https://mlsanity.com/paper/2305.13954/) (2023)
- [Task Facet Learning: A Structured Approach to Prompt Optimization](https://mlsanity.com/paper/2406.10504/) (2024)
- [System Prompt Optimization with Meta-Learning](https://mlsanity.com/paper/2505.09666/) (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)
- [Lifelong Sequence Generation with Dynamic Module Expansion and Adaptation](https://mlsanity.com/paper/2310.09886/) (2023)
- [MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning](https://mlsanity.com/paper/2405.11446/) (2024)
- [Context Tuning for In-Context Optimization](https://mlsanity.com/paper/2507.04221/) (2025)
- [Lifelong Event Detection with Embedding Space Separation and Compaction](https://mlsanity.com/paper/2404.02507/) (2024)
- [From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM](https://mlsanity.com/paper/2504.05801/) (2025)
- [Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering](https://mlsanity.com/paper/2506.06905/) (2025)

## Abstract (arXiv)

Prompt tuning (PT) which only tunes the embeddings of an additional sequence of tokens per task, keeping the pre-trained language model (PLM) frozen, has shown remarkable performance in few-shot learning. Despite this, PT has been shown to rely heavily on good initialization of the prompt embeddings. In this work, we study meta prompt tuning (MPT) to systematically explore how meta-learning can help improve (if it can) cross-task generalization in PT through learning to initialize the prompt embeddings from other relevant tasks. We empirically analyze a representative set of meta learning algorithms in a wide range of adaptation settings with different source/target task configurations on a large set of few-shot tasks. With extensive experiments and analysis, we demonstrate the effectiveness of MPT. We find the improvement to be significant particularly on classification tasks. For other kinds of tasks such as question answering, we observe that while MPT can outperform PT in most cases, it does not always outperform multi-task learning. We further provide an in-depth analysis from the perspective of task similarity.