Expired50% confidenceBenchmarkExact time
Stanford research shows that in complex debugging scenarios, the probability of LLM suggestions causing beginners to form incorrect mental models is approximately 23%, far higher than that of human tutors.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/16/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/14/2026(expired)
Sources
Related Claims
Unverified斯坦福大学2023年的一项研究发现，经过标准RLHF训练的模型面对用户错误观点时有高达78%的概率选择顺从或含糊其辞73% similarUnverified斯坦福大学人机交互研究组实验显示，即便自动化系统建议明显错误，参与者采纳错误建议的概率仍高达60%以上71% similarUnverified据斯坦福大学2024年的研究，即使是最先进的模型，在事实性任务中的幻觉率仍然在3%-15%之间波动71% similarUnverified斯坦福大学研究发现，在推理链关键步骤注入错误信息对最终答案的影响远小于预期70% similarUnverified研究显示，在专业技术领域，LLM 的幻觉率显著高于通用知识领域，因为训练数据中领域专家的纠错反馈相对稀少69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/530618API
curl https://kongchang.com/api/v1/knowledge/claims/530618MCP
get_claim(id=530618)