记录的问题
“How do AI search engines choose which sources to cite?”
- 产品
- Perplexity
- 界面
- Perplexity Search,已启用网络搜索
- 模型
- Perplexity 自动选择模型(未公开模型版本)
- 语言环境
- en-US(英文回答;中文界面)
- 观察到的回答
- 打开会话 ↗
- 观察日期
- 2026年11月15日 18:08 CST
- 全新对话
- 是
回答原文
Perplexity described source selection as query interpretation and search fan-out, retrieval and ranking, identification of passages that support the answer, then attribution. It said citation selection is related to search ranking but is not merely the ordinary results list. It highlighted exact-question relevance, passage-level support, reliability, accessibility and eligibility, freshness and extractable content, while noting that platforms do not publish a complete weighting formula. It warned that a retrieved page is not necessarily cited.
记录了 3 个来源
这次观察不能证明什么
本次使用已登录的免费账户在全新 Perplexity 对话中观察。渲染后的回答显示了 3 个带链接来源 URL,但采集时汇总来源面板没有加载。