UK AISIとEvalEvalが再現可能な評価レポートの共同開発に取り組む
UK AI Security Institute (AISI) は、EvalEval のインフラストラクチャを使用して評価結果を公開共有しており、より再現可能で検証可能な評価科学を支援しています。
01
根拠
- HHugging Face Blog企業開示2026-09-22
Why reproducible evaluation reporting matters What AISI is sharing Contribute to the shared mission About the EvalEval Coalition About the UK AI Security Institute Further reading The EvalEval Coalition is thrilled to share that the UK AI Security Institute (AISI) is using EvalE…
- HHugging Face Blog企業開示2026-09-22
Why reproducible evaluation reporting matters What AISI is sharing Contribute to the shared mission About the EvalEval Coalition About the UK AI Security Institute Further reading The EvalEval Coalition is thrilled to share that the UK AI Security Institute (AISI) is using EvalE…
- HHugging Face Blog企業開示2026-09-22
This builds naturally on AISI's work to make evaluation more efficient through OptStop , more statistically rigorous through HiBayES , and more standardised in areas including transcript analysis and capability elicitation. Together, AISI and EvalEval are working to diagnose gap…