From Code to Compliance: We’re building the first benchmark to hold AI accountable to human rights law.
The Human Rights Benchmark Project has successfully validated its methodology and achieved its first critical mission: revealing the extent of the LLM knowledge gap concerning human rights. The next phase is focused on scaling this standard to establish it as the industry norm.
The launch of the Human Rights Benchmark has yielded preliminary findings that validate the urgent need for this project: Leading LLMs possess a surprisingly low internalized representation of human rights law.
Creating a standard for AI accountability requires more than just a list of questions; it demands a “Gold Standard”methodology. Our Human Rights Benchmark Project is rooted in scientific rigor and deep domain expertise, ensuring we measure true legal understanding, not statistical artifacts.
For years, the AI community has wrestled with a measurement crisis. While standard benchmarks exist for technical performance, logical reasoning, and narrow ethical topics like social bias, they consistently miss the mark when it comes to systems making high-stakes decisions.
Join our AI & Equality community of students, academics, data scientists and AI practitioners who believe in responsible and fair AI.
