# Prompt Learning With Knowledge Memorizing Prototypes For Generalized Few-Shot Intent Detection

arXiv: https://arxiv.org/abs/2309.04971 · HTML: https://mlsanity.com/paper/2309.04971/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 10 Sep 2023.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning](https://mlsanity.com/paper/2011.01403/) (2020)
- [OpenPrompt: An Open-source Framework for Prompt-learning](https://mlsanity.com/paper/2111.01998/) (2021)
- [Are we ready for a new paradigm shift? A Survey on Visual Deep MLP](https://mlsanity.com/paper/2111.04060/) (2021)
- [The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking](https://mlsanity.com/paper/2203.00991/) (2022)
- [On the (In)Effectiveness of Large Language Models for Chinese Text Correction](https://mlsanity.com/paper/2307.09007/) (2023)
- [Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification](https://mlsanity.com/paper/1906.06678/) (2019)
- [Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking](https://mlsanity.com/paper/2210.10320/) (2022)
- [Contrastive Learning with Hard Negative Entities for Entity Set Expansion](https://mlsanity.com/paper/2204.07789/) (2022)
- [Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction](https://mlsanity.com/paper/2210.10442/) (2022)
- [Automatic Context Pattern Generation for Entity Set Expansion](https://mlsanity.com/paper/2207.08087/) (2022)
- [Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification](https://mlsanity.com/paper/2107.12262/) (2021)
- [Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection](https://mlsanity.com/paper/2010.02481/) (2020)
- [Active Relation Discovery: Towards General and Label-aware Open Relation Extraction](https://mlsanity.com/paper/2211.04215/) (2022)
- [Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking](https://mlsanity.com/paper/2306.12245/) (2023)

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

- [A Comparative Empirical Study of Catastrophic Forgetting Mitigation in Sequential Task Adaptation for Continual Natural Language Processing Systems](https://mlsanity.com/paper/2603.18641/) (2026)

## Abstract (arXiv)

Generalized Few-Shot Intent Detection (GFSID) is challenging and realistic because it needs to categorize both seen and novel intents simultaneously. Previous GFSID methods rely on the episodic learning paradigm, which makes it hard to extend to a generalized setup as they do not explicitly learn the classification of seen categories and the knowledge of seen intents. To address the dilemma, we propose to convert the GFSID task into the class incremental learning paradigm. Specifically, we propose a two-stage learning framework, which sequentially learns the knowledge of different intents in various periods via prompt learning. And then we exploit prototypes for categorizing both seen and novel intents. Furthermore, to achieve the transfer knowledge of intents in different stages, for different scenarios we design two knowledge preservation methods which close to realistic applications. Extensive experiments and detailed analyses on two widely used datasets show that our framework based on the class incremental learning paradigm achieves promising performance.