AI & Equality Pub-Talk | Human Rights Benchmark for LLMs | Savannah Thais

We’re in the process of developing a Human Rights Benchmark for Large Language Models LLMS— a tool designed to assess how well these systems align with core human rights principles.

Why now? As LLMs become embedded in decision-making systems, chatbots, and public services, we need more than accuracy—we need accountability. Our benchmark will explore whether these models treat all identities equally, respond consistently to rights-based questions, and avoid harmful omissions or bias.

Led by Savannah Thais, it is part of our core commitment: to build AI systems that respect dignity, uphold equality, and serve everyone—not just the powerful. In this Pub-Talk, Savannah will present the process and methodology of the benchmark.

Register via Circle: link TBC