[KongchangAI]
Unverified50% confidenceFactExact time

在生成阶段,使用Pydantic模型CitedAnswer(包含answer、citations、confidence、needs_clarification字段)配合LangChain的JsonOutputParser约束LLM输出结构化JSON,有助于抑制幻觉。

1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen

Sources

Related Entities

Cite This Claim

Stable URI
https://kongchang.com/claim/1008831
API
curl https://kongchang.com/api/v1/knowledge/claims/1008831
MCP
get_claim(id=1008831)