放大异常：人类如何选择未经证实的选项，大型语言模型如何避免这些选项

IF 2.5 3区心理学 Q2 PSYCHOLOGY, EDUCATIONAL

Creativity Research Journal Pub Date : 2024-06-17 DOI:10.1080/10400419.2024.2361217

Anthony K. Brandt

引用次数: 0

摘要

大型语言模型（LLMs）和人脑都会建立现实的内部模型，从而做出准确的预测。两者通常都倾向于选择具有最强记录的选项。然而，当...

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Amplifying the Anomaly: How Humans Choose Unproven Options and Large Language Models Avoid Them

Both large language models (LLMs) and the human brain develop internal models of reality to make accurate predictions. Both typically prefer choices with the strongest track records. However, when ...

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Creativity Research Journal Multiple-

CiteScore

5.10

自引率

7.70%

发文量

期刊介绍： Creativity Research Journal publishes high-quality, scholarly research capturing the full range of approaches to the study of creativity--behavioral, clinical, cognitive, crosscultural, developmental, educational, genetic, organizational, psychoanalytic, psychometrics, and social. Interdisciplinary research is also published, as is research within specific domains (e.g., art, science) and research on critical issues (e.g., aesthetics, genius, imagery, imagination, incubation, insight, intuition, metaphor, play, problem finding and solving). Integrative literature reviews and theoretical pieces that appreciate empirical work are extremely welcome, but purely speculative articles are not published. Readers are encouraged to send commentaries, comments, and evaluative book reviews.