Papers with full-shot

3 papers
BiKT: Enabling Bidirectional Knowledge Transfer Between Pretrained Models and Sequential Downstream Tasks (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing frameworks adapt from initial pretrained model to each downstream task directly, but ignore sequential nature of downstream tasks and feedback effect on pretrained models.
Approach: They propose a framework to enable bidirectional knowledge transfer between pretrained models and downstream tasks in rounds.
Outcome: The proposed framework improves on 9 GLUE datasets and 6 SuperGLUEs.
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.
RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction (2023.findings-emnlp)

Copied to clipboard

Challenge: Named Entity Recognition (NER) and Relation Extraction (RE) models have limited success when extracting general schemas such as quadruples and quintuples.
Approach: They propose a formal formulation that covers almost all extraction schemas and a Recursive Method with Explicit Schema Instructor for UIE.
Outcome: The proposed method shows strong performance under full-shot and few-shot settings and achieves state-of-the-art results on the tasks of extracting complex schemas.

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