对比GPT与DeepSeek模型的可信行为，发现性能提升背后隐藏的信任机制差异。
Reasoning and the Trusting Behavior of DeepSeek and GPT: An Experiment Revealing Hidden Fault Lines in Large Language Models
- 用博弈论信任模型测试LLM的决策行为
- o1-mini/o3-mini模型信任行为明显下降，而DeepSeek表现更优
- 适合关注AI系统可靠性的开发者与决策者
当大型语言模型（LLM）频繁出现性能提升或成本降低时，应用开发者需权衡是否切换至新模型。低切换门槛可能导致忽视模型间微妙的行为变化。我们通过经典博弈论行为经济学模型——信任实验，揭示OpenAI与DeepSeek模型在信任行为上的显著差异。结果表明，o1-mini与o3-mini模型在追求利润最大化和风险偏好时，其对未来信任回报的考量出现明显衰减，信任行为崩溃；而DeepSeek模型则展现出更复杂、更盈利的信任策略，源于对前瞻规划与心智理论的深层理解。鉴于LLM广泛用于高风险商业系统，本研究警示：过度依赖狭隘的性能基准存在风险，组织应将模型潜在“隐藏缺陷”分析纳入AI战略。
原文摘要 · Abstract (English)
When encountering increasingly frequent performance improvements or cost reductions from a new large language model (LLM), developers of applications leveraging LLMs must decide whether to take advantage of these improvements or stay with older tried-and-tested models. Low perceived switching frictions can lead to choices that do not consider more subtle behavior changes that the transition may induce. Our experiments use a popular game-theoretic behavioral economics model of trust to show stark differences in the trusting behavior of OpenAI's and DeepSeek's models. We highlight a collapse in the economic trust behavior of the o1-mini and o3-mini models as they reconcile profit-maximizing and risk-seeking with future returns from trust, and contrast it with DeepSeek's more sophisticated and profitable trusting behavior that stems from an ability to incorporate deeper concepts like forward planning and theory-of-mind. As LLMs form the basis for high-stakes commercial systems, our results highlight the perils of relying on LLM performance benchmarks that are too narrowly defined and suggest that careful analysis of their hidden fault lines should be part of any organization's AI strategy.
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。