[KongchangAI]
Unverified50% confidenceFactExact time

RAG系统存在'信源传递性信任'脆弱性——模型对检索到的文档默认给予信任并以自信语言转述,即便源文档虚假

1
Sources
50%
Confidence
Long-term
Relevance
7/7/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/198745
API
curl https://kongchang.com/api/v1/knowledge/claims/198745
MCP
get_claim(id=198745)