Unverified50% confidenceFactExact time
开放域问答中的幻觉率远高于封闭域分类任务
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedResearch shows that hallucination rate is negatively correlated with the knowledge density of the prompt; the richer and more precise the context provided in the prompt, the lower the probability that the model will generate fabricated content.69% similarUnverified模型规模越大，幻觉的表述往往越流畅、越具迷惑性，识别难度反而上升68% similarUnverifiedReAct相较纯CoT在知识密集型任务（多跳问答、实时信息检索）上表现显著更优，而在纯逻辑推理任务上差异相对较小67% similarUnverifiedLarge models output the most likely next word rather than precise retrieval of facts, which leads to hallucinations in domains with sparse coverage in the training data.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/514412API
curl https://kongchang.com/api/v1/knowledge/claims/514412MCP
get_claim(id=514412)