大型语言模型中的认知偏差：谨慎的乐观主义遭遇反潘格洛斯式的改良主义
Cognitive bias in large language models: Cautious optimism meets anti-Panglossian meliorism
AI总结：
本文探讨了大型语言模型中的认知偏差，提出对当前模型偏差普遍性保持谨慎乐观，同时承认真实偏差并努力减少，并分析了其哲学启示。
摘要：
关于大型语言模型中偏差的传统讨论聚焦于与不公密切相关的概念，尤其是影响边缘群体的不公。近期研究提出了评估大型语言模型输出中一系列认知偏差的新可能性，这些偏差在判断与决策研究中很常见。本文旨在从近期关于大型语言模型认知偏差的讨论中汲取两点教训：对当前模型中偏差的普遍性保持谨慎乐观，同时秉持反潘格洛斯式的改良主义，愿意承认某些真实偏差的存在并努力减少它们。我还探讨了此讨论对人类认知偏差的理性以及非代表性数据在驱动模型偏差中作用的哲学启示。
英文摘要：
Traditional discussions of bias in large language models focus on a conception of bias closely tied to unfairness, especially as affecting marginalized groups. Recent work raises the novel possibility of assessing the outputs of large language models for a range of cognitive biases familiar from research in judgment and decisionmaking. My aim in this paper is to draw two lessons from recent discussions of cognitive bias in large language models: cautious optimism about the prevalence of bias in current models coupled with an anti-Panglossian willingness to concede the existence of some genuine biases and work to reduce them. I draw out philosophical implications of this discussion for the rationality of human cognitive biases as well as the role of unrepresentative data in driving model biases.
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。
