ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models
Submission Type: Regular Long Paper
Submission Track: Theme Track: Large Language Models and the Future of NLP
Submission Track 2: Theme Track: Large Language Models and the Future of NLP
Keywords: robustness, safety, red teaming, large language models
TL;DR: ASSERT is an automated safety evaluation test suite aimed to provide fast and cost-effective insights into the failure modes of language models.
Abstract: As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various settings in which a user may invoke an intelligent system. This paper proposes ASSERT, Automated Safety Scenario Red Teaming, consisting of three methods -- semantically aligned augmentation, target bootstrapping, and adversarial knowledge injection. For robust safety evaluation, we apply these methods in the critical domain of AI safety to algorithmically generate a test suite of prompts covering diverse robustness settings -- semantic equivalence, related scenarios, and adversarial. We partition our prompts into four safety domains for a fine-grained analysis of how the domain affects model performance. Despite dedicated safeguards in existing state-of-the-art models, we find statistically significant performance differences of up to 11% in absolute classification accuracy among semantically related scenarios and error rates of up to 19% absolute error in zero-shot adversarial settings, raising concerns for users' physical safety.
Submission Number: 2458
Loading