Unverified50% confidenceFactExact time

LLMs do not verify the truthfulness of content, do not automatically know a user's private data, and do not proactively look up facts when generating responses.

1

Sources

50%

Confidence

Long-term

Relevance

10/12/2026

First Seen

Sources

Why Do LLMs Hallucinate? Understanding the Fundamental Reason RAG Exists

Related Entities

Related Claims

Unverified进入LLM上下文的外部内容（如会议转录、上传文档）应视为不可信数据源并进行清洗和隔离60% similar UnverifiedChina's Interim Measures for the Management of Generative Artificial Intelligence Services requires service providers not to generate false information.59% similar Unverified应把检索到的内容（邮件、附件、文档）视为不可信，敏感凭证不应出现在模型可见的上下文中58% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/1003564

API

curl https://kongchang.com/api/v1/knowledge/claims/1003564

MCP

get_claim(id=1003564)