Unverified50% confidenceBenchmarkExact time
普林斯顿大学Pranjal Aggarwal等人的论文《GEO: Generative Engine Optimization》发现，添加权威引用平均提升可见性30-40%，添加统计数据提升约25%，关键词堆砌几乎无效甚至产生负面效果
1
Sources
50%
Confidence
Long-term
Relevance
8/13/2026
First Seen
Sources
Related Claims
Unverified推测解码中当草稿通过率低于50%时，实际加速效果会大打折扣甚至产生负优化63% similarUnverifiedIthaca模型缺失文字预测准确率约62%，人类专家独立完成时约为25%，地理来源推断约71%，年代估算误差中位数约30年63% similarUnverifiedIncluding specific evaluation dimensions in prompts (such as format, word count, key points to cover, and items to exclude) can improve model output quality by an average of 30%–50% compared to vague prompts.62% similarUnverified当人类专家与AI（Ithaca）协作时，缺失文字预测准确率从专家独立工作的25%提升至约57%62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/742462API
curl https://kongchang.com/api/v1/knowledge/claims/742462MCP
get_claim(id=742462)