# MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detection

arXiv: https://arxiv.org/abs/2305.09335 · HTML: https://mlsanity.com/paper/2305.09335/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 16 May 2023.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [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)
- [True Few-Shot Learning with Language Models](https://mlsanity.com/paper/2105.11447/) (2021)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [MAVEN: A Massive General Domain Event Detection Dataset](https://mlsanity.com/paper/2004.13590/) (2020)
- [DEGREE: A Data-Efficient Generation-Based Event Extraction Model](https://mlsanity.com/paper/2108.12724/) (2021)
- [Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation](https://mlsanity.com/paper/1809.09078/) (2018)
- [Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection](https://mlsanity.com/paper/1910.11621/) (2019)
- [Prototypical Verbalizer for Prompt-based Few-shot Tuning](https://mlsanity.com/paper/2203.09770/) (2022)
- [Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding](https://mlsanity.com/paper/2110.07476/) (2021)
- [Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records](https://mlsanity.com/paper/1606.07953/) (2016)
- [Few-Shot Event Detection with Prototypical Amortized Conditional Random Field](https://mlsanity.com/paper/2012.02353/) (2020)
- [The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification](https://mlsanity.com/paper/2105.02778/) (2021)
- [Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection](https://mlsanity.com/paper/2105.09509/) (2021)
- [Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention](https://mlsanity.com/paper/2109.05747/) (2021)
- [Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification](https://mlsanity.com/paper/2108.12844/) (2021)
- [News Article Retrieval in Context for Event-centric Narrative Creation](https://mlsanity.com/paper/2106.16053/) (2021)
- [Pre-train, Interact, Fine-tune: A Novel Interaction Representation for Text Classification](https://mlsanity.com/paper/1909.11824/) (2019)

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

- [Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems](https://mlsanity.com/paper/2505.15741/) (2025)

## Abstract (arXiv)

Event detection (ED) is aimed to identify the key trigger words in unstructured text and predict the event types accordingly. Traditional ED models are too data-hungry to accommodate real applications with scarce labeled data. Besides, typical ED models are facing the context-bypassing and disabled generalization issues caused by the trigger bias stemming from ED datasets. Therefore, we focus on the true few-shot paradigm to satisfy the low-resource scenarios. In particular, we propose a multi-step prompt learning model (MsPrompt) for debiasing few-shot event detection, that consists of the following three components: an under-sampling module targeting to construct a novel training set that accommodates the true few-shot setting, a multi-step prompt module equipped with a knowledge-enhanced ontology to leverage the event semantics and latent prior knowledge in the PLMs sufficiently for tackling the context-bypassing problem, and a prototypical module compensating for the weakness of classifying events with sparse data and boost the generalization performance. Experiments on two public datasets ACE-2005 and FewEvent show that MsPrompt can outperform the state-of-the-art models, especially in the strict low-resource scenarios reporting 11.43% improvement in terms of weighted F1-score against the best-performing baseline and achieving an outstanding debiasing performance.