2 papers
cs.CL2024
Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks
Yue Zhou, Henry Peng Zou, Barbara Di Eugenio +1
We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterp…
cs.CL2024
Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models
Yue Zhou, Yada Zhu, Diego Antognini +2
This paper studies the relationship between the surface form of a mathematical problem and its solvability by large language models. We find that subtle alterations in the surface…