Publish fake stats, get cited in LLMs
An experiment demonstrated how easily fabricated statistics can be cited by large language models (LLMs). Using GPT-4.1, 50,000 invented statistics pages and 15,000 listicles were generated and published on stateglobe.com for about $50. These pages covered topics like SEO, content marketing, and e-commerce across 200 countries. The experiment highlighted that LLMs often prioritize specific, quotable numbers as evidence, even if those numbers are entirely made up, adding little real authority.
This experiment uniquely demonstrates how easily LLMs cite fabricated statistics, unlike previous studies that focused on factual recall or hallucination without direct evidence of citation.
时间与来源
时间显示为 UTC
显示时区:UTC
本地时区尚不可用,暂时显示 UTC。
收录当时偏移:UTC+02026年10月20日 14:00 UTC
- 收录
- 2026年10月20日 14:00
- 来源类型
- 未分类
- 判定依据
- 热度约为该来源近期上榜条目中位水平的 4.3 倍
- 指标对比
- 290 vs 中位 67(20 条基线样本)
- 检出时间
- 10/20 17:00
本站未收录正文。
前往源站阅读 →