Verified65% confidenceFactExact time
大模型幻觉是指语言模型生成看似合理但实际不正确或不存在的内容
3
Sources
65%
Confidence
Long-term
Relevance
4/12/2026
First Seen
Sources
Node.js实现AI Agent：用Function Call替代提示词工程
bilibili力气强4/12/2026
Related Entities
Related Claims
Unverified大模型幻觉是指LLM在生成内容时以高置信度输出看似合理但不符合用户需求的内容83% similarUnverified大语言模型幻觉是transformer自回归生成的内在属性，模型每步仅根据当前上下文概率分布采样下一个token，不具备对现实世界的接地能力79% similarVerified幻觉（Hallucination）指大语言模型生成看似合理但实际错误或无依据的内容，是当前所有LLM的共性问题，根源在于模型本质上是基于概率的文本生成器而非知识检索系统79% similarPartially VerifiedModel Hallucination refers to when large language models generate content that appears plausible but is actually incorrect, delivered with high confidence despite lacking factual support.79% similarVerified大模型幻觉的技术本质在于模型在训练时学习的是语言模式的概率分布而非事实本身78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/35614API
curl https://kongchang.com/api/v1/knowledge/claims/35614MCP
get_claim(id=35614)