# Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks

arXiv: https://arxiv.org/abs/2312.08726 · HTML: https://mlsanity.com/paper/2312.08726/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 59 references that are in the map.
- First posted on arXiv 14 Dec 2023.

## Builds on (most cited first, 30 of 42)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [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)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [Unified Structure Generation for Universal Information Extraction](https://mlsanity.com/paper/2203.12277/) (2022)
- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [Few-NERD: A Few-Shot Named Entity Recognition Dataset](https://mlsanity.com/paper/2105.07464/) (2021)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [BertGCN: Transductive Text Classification by Combining GCN and BERT](https://mlsanity.com/paper/2105.05727/) (2021)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Prompt-Learning for Fine-Grained Entity Typing](https://mlsanity.com/paper/2108.10604/) (2021)
- [PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks](https://mlsanity.com/paper/2202.12499/) (2022)
- [Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words](https://mlsanity.com/paper/2205.05092/) (2022)
- [Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER](https://mlsanity.com/paper/2110.08454/) (2021)
- [ERNIE-Doc: A Retrospective Long-Document Modeling Transformer](https://mlsanity.com/paper/2012.15688/) (2020)
- [HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification](https://mlsanity.com/paper/2204.13413/) (2022)
- [METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals](https://mlsanity.com/paper/2204.06644/) (2022)
- [Improving Paraphrase Detection with the Adversarial Paraphrasing Task](https://mlsanity.com/paper/2106.07691/) (2021)

## Built on by (most cited first, 1 of 1)

- [MPL: Multiple Programming Languages with Large Language Models for Information Extraction](https://mlsanity.com/paper/2505.16107/) (2025)

## Abstract (arXiv)

Textual label names (descriptions) are typically semantically rich in many natural language understanding (NLU) tasks. In this paper, we incorporate the prompting methodology, which is widely used to enrich model input, into the label side for the first time. Specifically, we propose a Mask Matching method, which equips an input with a prompt and its label with another, and then makes predictions by matching their mask representations. We evaluate our method extensively on 8 NLU tasks with 14 datasets. The experimental results show that Mask Matching significantly outperforms its counterparts of fine-tuning and conventional prompt-tuning, setting up state-of-the-art performances in several datasets. Mask Matching is particularly good at handling NLU tasks with large label counts and informative label names. As pioneering efforts that investigate the label-side prompt, we also discuss open issues for future study.