Unverified50% confidenceTradeoffExact time
Large language models still face hallucination problems in information extraction tasks, potentially completing information not explicitly mentioned in conversations and causing inaccurate CRM data.
1
Sources
50%
Confidence
Long-term
Relevance
9/4/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLarge language models have hallucination problems and may fabricate non-existent references, invent experimental data, or provide incorrect statistical figures.80% similarUnverified在涉及代码执行状态、外部系统交互、实时数据查询等需要接地气的任务上，幻觉率显著高于纯文本写作或知识问答类任务71% similarUnverified混淆情节记忆与语义记忆的存储介质是常见架构错误：将需精确检索的任务状态放入向量库会引入近似误差，将需语义检索的知识放入关系数据库会导致召回率低下69% similarUnverified低质量的知识库会导致幻觉式引用，即模型看似使用知识库内容实则引用了错误或无关片段67% similarUnverified基准过拟合和数据污染会导致模型通过记忆而非真正理解获得高分，使公开基准分数可信度存疑66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/852895API
curl https://kongchang.com/api/v1/knowledge/claims/852895MCP
get_claim(id=852895)