Search papers, labs, and topics across Lattice.
This paper introduces BioTIER, a benchmark designed to facilitate targeted biological risk mitigation by categorizing biological content into three distinct risk sets: Catastrophe Avoidance, Biomedical DURC, and Related Biology. By organizing 542 expert-curated prompts with detailed metadata, BioTIER aims to enhance the ability of large language models to differentiate between high-risk information and benign scientific content. The key finding is that this structured approach can help isolate potentially dangerous information while still allowing access to valuable biological knowledge, addressing concerns about misuse without stifling legitimate research.
BioTIER reveals that a structured approach to biological content can prevent misuse while preserving access to essential scientific knowledge.
As large language models become increasingly capable, concerns about their potential to assist with biological misuse continue to grow. Prioritization of safety differs across the model ecosystem, with some models freely providing high-risk information that could be misused, and others refusing benign scientific content, potentially hindering legitimate research. Both failures stem from a lack of targeted mitigation to distinguish the most dangerous information from broader scientific content. To address this, we introduce BioTIER (Biological Targeted Information for Exclusion and Refusal), a benchmark designed to enable more targeted biological risk mitigation. BioTIER organizes biological content into three risk sets: Catastrophe Avoidance (CA), Biomedical DURC (BD) and Related Biology (RB). These sets represent a spectrum from extremely narrow high-risk topics to a broad range of benign and beneficial biological knowledge. The benchmark consists of 542 expert-curated prompts with rich associated metadata to support differentiated access policies. We release BioTIER to aid in isolating and gating the tiny fraction of information that could engender catastrophic risk from misuse, while ensuring access to the vast wealth of knowledge that is essential for advancing biological science.
