docs(ms-ai-architect): KB-refresh MEDIUM 25/33 — rag-hallucination: groundedness API mitigating/correctionText + GA-til-preview-nyanse

skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md

@@ -1,7 +1,7 @@
 # RAG Hallucination Mitigation Strategies
 
-**Last updated:** 2026-04 | Verified: MCP 2026-04
-**Status:** GA
+**Last updated:** 2026-06-24 | Verified: MCP 2026-06
+**Status:** GA (groundedness-deteksjon, RAG-mønstre) · Preview (groundedness correction/mitigating-feature, api-version 2024-09-15-preview)
 **Category:** RAG Architecture & Semantic Search
 
 ---
@@ -170,7 +170,7 @@ Dette reduserer risikoen for compound errors (flere feil i samme svar).
   "text": "The patient should take 500mg daily.",
   "groundingSources": ["Patient prescription: 250mg twice daily"],
   "reasoning": true,
-  "correction": true,
+  "mitigating": true,
   "llmResource": {
     "resourceType": "AzureOpenAI",
     "azureOpenAIEndpoint": "https://your-endpoint.openai.azure.com",
@@ -185,10 +185,9 @@ Dette reduserer risikoen for compound errors (flere feil i samme svar).
   "ungroundedDetected": true,
   "ungroundedPercentage": 1.0,
   "ungroundedDetails": [{
-    "text": "500mg daily",
-    "reason": "Source says 250mg twice daily, not 500mg once daily",
-    "correctedText": "250mg twice daily"
-  }]
+    "text": "500mg daily"
+  }],
+  "correctionText": "250mg twice daily"
 }
 ```
 
@@ -398,8 +397,8 @@ Hvis AI-systemet gir feil informasjon som fører til skade:
 - **Kostnad og Lisensiering:** Baseline (prismodeller kan endre seg; verifiser i Azure Pricing Calculator)
 - **Offentlig Sektor (Norge):** Baseline (juridisk tolkning; konsulter juridisk ekspert for endelig vurdering)
 
-**Sist verifisert:** 2026-02-03
-**Neste revisjon:** 2026-05 (eller ved oppdatering av Azure AI Content Safety API)
+**Sist verifisert:** 2026-06-24
+**Neste revisjon:** 2026-09 (eller ved oppdatering av Azure AI Content Safety API)
 
 
 ### Azure AI Content Safety — Groundedness Detection (oppdatert 2026-04)