# Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation

arXiv: https://arxiv.org/abs/2503.04299 · HTML: https://mlsanity.com/paper/2503.04299/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 13 of 13)

- [Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models](https://mlsanity.com/paper/2408.08926/) (2024)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [LLM Agents can Autonomously Exploit One-day Vulnerabilities](https://mlsanity.com/paper/2404.08144/) (2024)
- [BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices](https://mlsanity.com/paper/2411.12990/) (2024)
- [AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks](https://mlsanity.com/paper/2403.01038/) (2024)
- [CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence](https://mlsanity.com/paper/2406.07599/) (2024)
- [CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models](https://mlsanity.com/paper/2408.01605/) (2024)
- [Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools](https://mlsanity.com/paper/2306.13952/) (2023)
- [Can large language models democratize access to dual-use biotechnology?](https://mlsanity.com/paper/2306.03809/) (2023)
- [Will releasing the weights of future large language models grant widespread access to pandemic agents?](https://mlsanity.com/paper/2310.18233/) (2023)
- [Risk assessment at AGI companies: A review of popular risk assessment techniques from other safety-critical industries](https://mlsanity.com/paper/2307.08823/) (2023)
- [Safety case template for frontier AI: A cyber inability argument](https://mlsanity.com/paper/2411.08088/) (2024)
- [A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management](https://mlsanity.com/paper/2502.06656/) (2025)

## Built on by (most cited first, 4 of 4)

- [Measuring AI Ability to Complete Long Software Tasks](https://mlsanity.com/paper/2503.14499/) (2025)
- [Scalable Delphi: Large Language Models for Structured Risk Estimation](https://mlsanity.com/paper/2602.08889/) (2026)
- [A Theoretical Framework for Adaptive Utility-Weighted Benchmarking](https://mlsanity.com/paper/2602.12356/) (2026)
- [AI Persuasion as a Threat to Human Control](https://mlsanity.com/paper/2609.14796/) (2026)

## Abstract (arXiv)

The literature and multiple experts point to many potential risks from large language models (LLMs), but there are still very few direct measurements of the actual harms posed. AI risk assessment has so far focused on measuring the models' capabilities, but the capabilities of models are only indicators of risk, not measures of risk. Better modeling and quantification of AI risk scenarios can help bridge this disconnect and link the capabilities of LLMs to tangible real-world harm. This paper makes an early contribution to this field by demonstrating how existing AI benchmarks can be used to facilitate the creation of risk estimates. We describe the results of a pilot study in which experts use information from Cybench, an AI benchmark, to generate probability estimates. We show that the methodology seems promising for this purpose, while noting improvements that can be made to further strengthen its application in quantitative AI risk assessment.