kenneth.computer

Home

❯

research

❯

artifacts

❯

technical-reports

technical-reports

1 item under this folder.

  • Feb 15, 2026

    Multi-judge behavioral evaluation of GLM-5

    • multi-judge
    • llm-as-judge
    • judge-reliability
    • behavioral-evals
    • petri
    • alignment
    • glm-5

Created with Quartz v5.0.0 | Kenneth Francis Cavanagh © 2026