paper-with-me

홈 › Papers

Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention

2021-09-13 · EMNLP 2021 11 · Jiawei Chen, Hongyu Lin, Xianpei Han, Le Sun

Event detection has long been troubled by the \emph{trigger curse}: overfitting the trigger will harm the generalization ability while underfitting it will hurt the detection performance. This problem is even more severe in few-shot scenario. In this paper, we identify and solve the trigger curse problem in few-shot event detection (FSED) from a causal view. By formulating FSED with a structural causal model (SCM), we found that the trigger is a confounder of the context and the result, which makes previous FSED methods much easier to overfit triggers. To resolve this problem, we propose to intervene on the context via backdoor adjustment during training. Experiments show that our method significantly improves the FSED on ACE05, MAVEN and KBP17 datasets.

📄 PDF Abstract BibTeX arXiv:2109.05747

Code (1)

chen700564/causalfsed 공식 구현 pytorch

Tasks

Event Detection

Similar Papers 제목 키워드 기반

Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning

2024-03-30 · Xiaopeng Xie, Ming Yan, Xiwen Zhou, Chenlong Zhao 외

Prompt-based learning paradigm has demonstrated remarkable efficacy in enhancing the adaptability of pretrained language models (PLMs), particularly in few-shot scenarios. However, this learning paradigm has been shown t…

Data AugmentationFew-Shot Text Classificationtext-classificationText Classification

HoneypotNet: Backdoor Attacks Against Model Extraction

2025-01-02 · Yixu Wang, Tianle Gu, Yan Teng, Yingchun Wang 외

Model extraction attacks are one type of inference-time attacks that approximate the functionality and performance of a black-box victim model by launching a certain number of queries to the model and then leveraging the…

Backdoor AttackmodelModel extraction

Does Few-shot Learning Suffer from Backdoor Attacks?

2023-12-31 · Xinwei Liu, Xiaojun Jia, Jindong Gu, Yuan Xun 외

The field of few-shot learning (FSL) has shown promising results in scenarios where training data is limited, but its vulnerability to backdoor attacks remains largely unexplored. We first explore this topic by first eva…

Backdoor AttackFew-Shot Learning

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models

2023-05-02 · Shuai Zhao, Jinming Wen, Luu Anh Tuan, Junbo Zhao 외

The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied,…

Backdoor AttackFew-Shot Text Classificationtext-classificationText Classification

Potion: Towards Poison Unlearning

2024-06-13 · Stefan Schoepf, Jack Foster, Alexandra Brintrup

Adversarial attacks by malicious actors on machine learning systems, such as introducing poison triggers into training datasets, pose significant risks. The challenge in resolving such an attack arises in practice when o…

Machine Unlearning