← Search

Yanshan Wang

2 accepted papers

2024

TrojFSP: Trojan Insertion in Few-shot Prompt Tuning

NAACL 2024long

Prompt tuning is one of the most effective solutions to adapting a fixed pre-trained language model (PLM) for various downstream tasks, especially with only a few input samples. However, the security issues, e.g., Trojan attacks, of prompt tuning on a few data samples are not well-studied. Transferr…

2023

Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses

ACL 2023findings

A human decision-maker benefits the most from an AI assistant that corrects for their biases. For problems such as generating interpretation of a radiology report given findings, a system predicting only highly likely outcomes may be less useful, where such outcomes are already obvious to the user.…

Cited by 10SourcePDFScholar