# ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization

arXiv: https://arxiv.org/abs/2201.06910 · HTML: https://mlsanity.com/paper/2201.06910/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 18 Jan 2022.

## Builds on (most cited first, 30 of 33)

- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [SelfReg: Self-supervised Contrastive Regularization for Domain Generalization](https://mlsanity.com/paper/2104.09841/) (2021)
- [ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning](https://mlsanity.com/paper/2111.10952/) (2021)
- [CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP](https://mlsanity.com/paper/2104.08835/) (2021)
- [PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation](https://mlsanity.com/paper/2104.12369/) (2021)
- [Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections](https://mlsanity.com/paper/2104.04670/) (2021)
- [Domain Agnostic Learning with Disentangled Representations](https://mlsanity.com/paper/1904.12347/) (2019)
- [Self-training Improves Pre-training for Natural Language Understanding](https://mlsanity.com/paper/2010.02194/) (2020)
- [Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning](https://mlsanity.com/paper/2004.01959/) (2020)
- [CPM: A Large-scale Generative Chinese Pre-trained Language Model](https://mlsanity.com/paper/2012.00413/) (2020)
- [Domain Generalization via Gradient Surgery](https://mlsanity.com/paper/2108.01621/) (2021)

## Built on by (most cited first, 30 of 54)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering](https://mlsanity.com/paper/2212.10375/) (2022)
- [What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?](https://mlsanity.com/paper/2204.05832/) (2022)
- [Revisiting Relation Extraction in the era of Large Language Models](https://mlsanity.com/paper/2305.05003/) (2023)
- [NEFTune: Noisy Embeddings Improve Instruction Finetuning](https://mlsanity.com/paper/2310.05914/) (2023)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases](https://mlsanity.com/paper/2303.14742/) (2023)
- [Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning](https://mlsanity.com/paper/2402.04833/) (2024)
- [LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement](https://mlsanity.com/paper/2403.15042/) (2024)
- [Improving In-Context Few-Shot Learning via Self-Supervised Training](https://mlsanity.com/paper/2205.01703/) (2022)
- [Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks](https://mlsanity.com/paper/2311.00288/) (2023)
- [InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning](https://mlsanity.com/paper/2205.12673/) (2022)
- [Augmented Large Language Models with Parametric Knowledge Guiding](https://mlsanity.com/paper/2305.04757/) (2023)
- [BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing](https://mlsanity.com/paper/2206.15076/) (2022)
- [Robustness of Learning from Task Instructions](https://mlsanity.com/paper/2212.03813/) (2022)
- [Chinese Open Instruction Generalist: A Preliminary Release](https://mlsanity.com/paper/2304.07987/) (2023)
- [GenQA: Generating Millions of Instructions from a Handful of Prompts](https://mlsanity.com/paper/2406.10323/) (2024)
- [Large Language Model Instruction Following: A Survey of Progresses and Challenges](https://mlsanity.com/paper/2303.10475/) (2023)
- [Interactive Natural Language Processing](https://mlsanity.com/paper/2305.13246/) (2023)
- [An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models](https://mlsanity.com/paper/2401.06692/) (2024)
- [Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation](https://mlsanity.com/paper/2304.07854/) (2023)
- [UnifieR: A Unified Retriever for Large-Scale Retrieval](https://mlsanity.com/paper/2205.11194/) (2022)
- [A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model](https://mlsanity.com/paper/2304.08109/) (2023)
- [LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models](https://mlsanity.com/paper/2309.09506/) (2023)

## Abstract (arXiv)

We propose a multitask pretraining approach ZeroPrompt for zero-shot generalization, focusing on task scaling and zero-shot prompting. While previous models are trained on only a few dozen tasks, we scale to 1,000 tasks for the first time using real-world data. This leads to a crucial discovery that task scaling can be an efficient alternative to model scaling; i.e., the model size has little impact on performance with an extremely large number of tasks. Our results show that task scaling can substantially improve training efficiency by 30 times in FLOPs. Moreover, we present a prompting method that incorporates a genetic algorithm to automatically search for the best prompt for unseen tasks, along with a few other improvements. Empirically, ZeroPrompt substantially improves both the efficiency and the performance of zero-shot learning across a variety of academic and production datasets.