arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.09193cs.CLcs.AIcs.HC
收藏

非理性与大语言模型中的认知偏差

(Ir)rationality and Cognitive Biases in Large Language Models

University College London(伦敦大学);University of Bologna(博洛尼亚大学)

Olivia Macmillan-Scott, Mirco Musolesi

AI总结:

本文通过心理学文献中的任务评估七种语言模型,发现其在非理性表现上与人类相似,但表现形式不同,且存在响应不一致的额外非理性特征。

摘要:

大型语言模型(LLMs)表现出理性推理吗?LLMs已被证明包含人类偏见,因为它们训练的数据中包含这些偏见;这种偏见是否反映在理性推理中尚不明确。在本文中,我们通过认知心理学文献中的任务评估了七种语言模型,以回答这个问题。我们发现,像人类一样,LLMs在这些任务中表现出非理性。然而,这种非理性表现的方式并不反映人类所展示的方式。当LLMs在这些任务中给出错误答案时,它们往往以与人类偏见不同的方式错误。此外,LLMs还揭示了响应中显著不一致性的额外非理性层。除了实验结果外,本文还希望通过展示如何评估和比较这些模型的不同能力,做出方法论上的贡献,特别是在理性推理方面。

英文摘要:

Do large language models (LLMs) display rational reasoning? LLMs have been shown to contain human biases due to the data they have been trained on; whether this is reflected in rational reasoning remains less clear. In this paper, we answer this question by evaluating seven language models using tasks from the cognitive psychology literature. We find that, like humans, LLMs display irrationality in these tasks. However, the way this irrationality is displayed does not reflect that shown by humans. When incorrect answers are given by LLMs to these tasks, they are often incorrect in ways that differ from human-like biases. On top of this, the LLMs reveal an additional layer of irrationality in the significant inconsistency of the responses. Aside from the experimental results, this paper seeks to make a methodological contribution by showing how we can assess and compare different capabilities of these types of models, in this case with respect to rational reasoning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑