open/ms-ai-architect
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions

docs(ms-ai-architect): KB-refresh HIGH 7/11 — bias-detection: image-modeller Medium-terskel (ikke Low) verifisert mot default-safety-policies

Browse source
This commit is contained in:
Kjell Tore Guttormsen 2026-06-24 10:44:36 +02:00
commit 0bb0e757b0
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
skills/ms-ai-governance/references/responsible-ai/bias-detection-mitigation-strategies.md
View file

@ -1,6 +1,6 @@
# Bias Detection and Mitigation - Practical Approaches
**Last updated:** 2026-02
**Last updated:** 2026-06-24 | Verified: MCP 2026-06-24
**Status:** GA
**Category:** Responsible AI & Governance
@ -105,7 +105,7 @@ Helhetlig plattform som integrerer seks verktøy for model debugging og bias ass
**Default konfigurasjon:**
- **Text models:** Medium severity threshold (blokkerer medium og høyere)
- **Image models:** Low severity threshold (mer restriktivt)
- **Image models:** Medium severity threshold (samme terskel som text models for alle fire kategorier)
- Content filtering skjer synkront under inferens
- Separat fakturering etter [Azure AI Content Safety pricing](https://azure.microsoft.com/pricing/details/cognitive-services/content-safety/)