# Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models

arXiv: https://arxiv.org/abs/2407.13059 · HTML: https://mlsanity.com/paper/2407.13059/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 88 references that are in the map.
- First posted on arXiv 25 May 2024.

## Builds on (most cited first, 8 of 8)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4](https://mlsanity.com/paper/2311.07361/) (2023)
- [On the Societal Impact of Open Foundation Models](https://mlsanity.com/paper/2403.07918/) (2024)
- [Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools](https://mlsanity.com/paper/2306.13952/) (2023)
- [Will releasing the weights of future large language models grant widespread access to pandemic agents?](https://mlsanity.com/paper/2310.18233/) (2023)

## Built on by (most cited first, 10 of 10)

- [Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs](https://mlsanity.com/paper/2512.05648/) (2025)
- [Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning](https://mlsanity.com/paper/2511.19299/) (2025)
- [A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models](https://mlsanity.com/paper/2608.02684/) (2026)
- [Securing Dual-Use Pathogen Data of Concern](https://mlsanity.com/paper/2602.08061/) (2026)
- [Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration](https://mlsanity.com/paper/2609.16204/) (2026)
- [Mutually Assured Deregulation](https://mlsanity.com/paper/2508.12300/) (2025)
- [BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment](https://mlsanity.com/paper/2607.05462/) (2026)
- [Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap](https://mlsanity.com/paper/2607.12113/) (2026)
- [Magnet: Detecting Cross-Session AI Misuse Through Capability Accumulation](https://mlsanity.com/paper/2608.02518/) (2026)
- [Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance](https://mlsanity.com/paper/2609.16213/) (2026)

## Abstract (arXiv)

As a result of rapidly accelerating AI capabilities, over the past year, national governments and multinational bodies have announced efforts to address safety, security and ethics issues related to AI models. One high priority among these efforts is the mitigation of misuse of AI models. Many biologists have for decades sought to reduce the risks of scientific research that could lead, through accident or misuse, to high-consequence disease outbreaks. Scientists have carefully considered what types of life sciences research have the potential for both benefit and risk (dual-use), especially as scientific advances have accelerated our ability to engineer organisms and create novel variants of pathogens. Here we describe how previous experience and study by scientists and policy professionals of dual-use capabilities in the life sciences can inform risk evaluations of AI models with biological capabilities. We argue that AI model evaluations should prioritize addressing high-consequence risks (those that could cause large-scale harm to the public, such as pandemics), and that these risks should be evaluated prior to model deployment so as to allow potential biosafety and/or biosecurity measures. Scientists' experience with identifying and mitigating dual-use biological risks can help inform new approaches to evaluating biological AI models. Identifying which AI capabilities post the greatest biosecurity and biosafety concerns is necessary in order to establish targeted AI safety evaluation methods, secure these tools against accident and misuse, and avoid impeding immense potential benefits.