Go to NeurIPS 2024 Workshop SafeGenAi homepageAEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
As Large Language Models (LLMs) and generative AI become increasingly widespread, concerns about content safety have grown in parallel. Currently, there is a clear lack of high-quality, human-annotated datasets that address the full spectrum of LLM-related safety risks and are usable for commercial applications. To bridge this gap, we propose a comprehensive and adaptable taxonomy for categorizing safety risks, structured into 12 top-level hazard categories with an extension to 9 fine-grained subcategories. This taxonomy is designed to meet the diverse requirements of downstream users, offering more granular and flexible tools for managing various risk types. Using a hybrid data generation pipeline that combines human annotations with a multi-LLM "jury" system to assess the safety of responses we obtain AEGIS 2.0, a carefully curated collection of 30,947 samples of human-LLM interactions, annotated according to our proposed taxonomy. To validate its effectiveness, we demonstrate that several lightweight models, trained using parameter-efficient techniques on A, achieve performance competitive with leading safety models fully fine-tuned on much larger, non-commercial datasets generated leveraging GPT-4. Additionally, we introduce a novel training blend that combines topic following data with safety data. This approach enhances the adaptability of guard models, enabling them to generalize to new risk categories defined during inference. We intend to release AEGIS 2.0 to the research community to aid in safety guardrailing of LLMs.