Papers with few-shot text classification tasks

3 papers
PromptDA: Label-guided Data Augmentation for Prompt-based Few Shot Learners (2023.eacl-main)

Copied to clipboard

Challenge: Existing studies on prompt-based few-shot tuning focus on deriving proper label words with a verbalizer or generating prompt templates to elicit semantics from PLMs.
Approach: They propose a framework that leverages label semantics for prompt-based tuning.
Outcome: The proposed framework improves on few-shot text classification tasks by leveraging label semantics and data augmentation.
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: ProAttack is a novel and efficient method for performing clean-label backdoor attacks based on the prompt, which uses the prompt itself as a trigger.
Approach: They propose a method for performing clean-label backdoor attacks based on the prompt, which uses the prompt itself as a trigger.
Outcome: The proposed method achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings.
Shortcuts Arising from Contrast: Towards Effective and Lightweight Clean-Label Attacks in Prompt-Based Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Prompt-based learning paradigms are vulnerable to backdoor attacks, requiring false activations and false data augmentation.
Approach: They propose a method that uses triggers to create stronger shortcuts by leveraging activation values and data selection strategies to create the shortcuts.
Outcome: The proposed method is based on the concept that a backdoor acts as a shortcut and can achieve high effectiveness and stealthiness at low poisoning rates.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations