研究大模型在九类认知偏差中的表现，揭示其推理可靠性问题。
Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI
- 通过1500次实验测试三款大模型在九类认知偏差上的表现
- GPT-4o表现最佳，Llama 3.1频繁出错且逻辑矛盾
- 强调未来AGI需融合统计思维与伦理设计
本研究考察了三种大型语言模型（GPT-4o、Gemma 2、Llama 3.1）在九类经典认知偏差中的表现。通过1500次实验评估模型响应的一致性与合理性。结果表明，GPT-4o整体表现最优；Gemma 2在沉没成本谬误和前景理论相关任务中表现突出，但跨偏差表现波动较大；而Llama 3.1始终表现最差，过度依赖启发式规则，存在频繁不一致与自相矛盾。研究揭示了当前大模型在实现稳健、可泛化推理方面的挑战，强调未来通用人工智能（AGI）的发展必须融入统计推理能力与伦理考量。
原文摘要 · Abstract (English)
We investigate the presence of cognitive biases in three large language models (LLMs): GPT-4o, Gemma 2, and Llama 3.1. The study uses 1,500 experiments across nine established cognitive biases to evaluate the models' responses and consistency. GPT-4o demonstrated the strongest overall performance. Gemma 2 showed strengths in addressing the sunk cost fallacy and prospect theory, however its performance varied across different biases. Llama 3.1 consistently underperformed, relying on heuristics and exhibiting frequent inconsistencies and contradictions. The findings highlight the challenges of achieving robust and generalizable reasoning in LLMs, and underscore the need for further development to mitigate biases in artificial general intelligence (AGI). The study emphasizes the importance of integrating statistical reasoning and ethical considerations in future AI development.
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。