{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/assert-automated-safety-scenario-red-teaming","title":"ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models","arxiv_id":"2310.09624","date":"2023-10-14","proceeding":null,"authors":["Alex Mei","Sharon Levy","William Yang Wang"],"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.","url_abs":"https://arxiv.org/abs/2310.09624v2","url_pdf":"https://arxiv.org/pdf/2310.09624v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"assert-automated-safety-scenario-red-teaming","repo_url":"https://github.com/alexmeigz/assert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"red-teaming","task_name":"Red Teaming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.09624","atlas_url":"https://app.syntology.ai/?focus=2310.09624","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}