研究大模型人格如何影响认知偏差，发现尽责与随和性格可提升纠错效果。
Investigating the Impact of LLM Personality on Cognitive Bias Manifestation in Automated Decision-Making Tasks
- 通过分析人格特质对偏差的影响，揭示不同模型对纠错策略的响应差异。
- 识别出六种主要认知偏差，沉没成本与群体归因偏差影响较小。
- 适合关注AI公平性、决策可靠性及个性化调优的研究者参考。
大型语言模型（LLMs）在决策任务中的应用日益广泛，但其对认知偏差的敏感性仍是严峻挑战。本研究探讨人格特质如何影响这些偏差，并评估不同模型架构下缓解策略的有效性。研究发现存在六种常见认知偏差，其中沉没成本偏差和群体归因偏差影响较小。人格特质在放大或减弱偏差方面起关键作用，显著影响模型对去偏技术的响应。值得注意的是，尽责性（Conscientiousness）和随和性（Agreeableness）可能普遍增强去偏策略的效果，表明具备此类特质的模型更易接受纠正措施。研究强调了人格驱动的偏差动态的重要性，凸显了针对特定场景设计去偏方法的必要性，以提升人工智能辅助决策的公平性与可靠性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly used in decision-making, yet their susceptibility to cognitive biases remains a pressing challenge. This study explores how personality traits influence these biases and evaluates the effectiveness of mitigation strategies across various model architectures. Our findings identify six prevalent cognitive biases, while the sunk cost and group attribution biases exhibit minimal impact. Personality traits play a crucial role in either amplifying or reducing biases, significantly affecting how LLMs respond to debiasing techniques. Notably, Conscientiousness and Agreeableness may generally enhance the efficacy of bias mitigation strategies, suggesting that LLMs exhibiting these traits are more receptive to corrective measures. These findings address the importance of personality-driven bias dynamics and highlight the need for targeted mitigation approaches to improve fairness and reliability in AI-assisted decision-making.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。