1 citations · 2 across the 2 of their papers we have counts for
4 papers
Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
Yik Siu Chan, Zheng-Xin Yong, Stephen H. Bach
Reasoning language models improve performance on complex tasks by generating long chains of thought (CoTs), but this process can also increase harmful outputs in adversarial settin…
MIB: A Mechanistic Interpretability Benchmark
Aaron Mueller, Atticus Geiger, Sarah Wiegreffe +20
How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretabili…
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Yik Siu Chan, Narutatsu Ri, Yuxin Xiao +1
Despite extensive safety alignment efforts, large language models (LLMs) remain vulnerable to jailbreak attacks that elicit harmful behavior. While existing studies predominantly f…
A Demonstration of Adaptive Collaboration of Large Language Models for Medical Decision-Making
Yubin Kim, Chanwoo Park, Hyewon Jeong +7
Medical Decision-Making (MDM) is a multi-faceted process that requires clinicians to assess complex multi-modal patient data patient, often collaboratively. Large Language Models (…