No Offense Taken: Eliciting Offensiveness from Language Models

Abstract: This work was completed in May 2022. For safe and reliable deployment of LLMs in the real world, testing needs to be robust. This robustness can be characterized by the difficulty and diversity of the test cases we evaluate these models on. Limitations in human-in-the-loop test case generation has prompted an advent of automated test case generation approaches. In particular, we focus on Red Teaming LLMs with LLMs by Perez et al.(2022). Our contributions include developing a pipeline for automated test case generation via red teaming that leverages publicly available smaller LMs, experimenting with different target LMs and red classifiers, and generating a corpus of test cases that can help in eliciting offensive responses from widely deployed LMs and identifying their failure modes.