← Search

Dan Valentine

2 accepted papers

2025

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

ICLR 2025poster

The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of vision-language models (VLMs) that generate text outputs conditi…

Cited by 3SourcePDFScholar
2024

Debating with More Persuasive LLMs Leads to More Truthful Answers

ICML 2024oral

Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will surpass human expertise, and the role of human evaluation will evolve into non-experts overseeing experts. In anticipatio…