Seeing the Goal, Missing the Truth: Human Accountability for AI Bias
收藏NBER2026-05-01 更新2026-05-09 收录
下载链接：
https://www.nber.org/papers/w35142
下载链接
链接失效反馈官方服务：
资源简介：
This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock returns or earnings) of LLM outputs leads the LLM to
提供机构：
美国国家经济研究局
创建时间：
2026-05-01
