研究大模型在价格谈判中如何受锚定效应影响
How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations
- 让大模型扮演卖家，测试锚定效应的影响
- 推理能力强的模型更不易受锚定效应干扰
- 性格特征与锚定效应无关，适合安全应用研究
认知偏差在人类中已有广泛研究，但在大语言模型（LLMs）中的表现也影响其在现实应用中的可靠性。本文以价格谈判场景为案例，研究了大模型中锚定效应的作用。我们指令卖家大模型代理运用锚定效应，并通过客观与主观双维度评估谈判效果。实验表明，大模型会像人类一样受到锚定效应影响。进一步分析发现，具备较强推理能力的模型更少受该效应干扰，长链思维可缓解锚定效应；但性格特质与锚定敏感性无显著关联。这些发现有助于深入理解大模型中的认知偏差，推动其在社会中安全、负责任的应用。
原文摘要 · Abstract (English)
Cognitive biases, well-studied in humans, can also be observed in LLMs, affecting their reliability in real-world applications. This paper investigates the anchoring effect in LLM-driven price negotiations. To this end, we instructed seller LLM agents to apply the anchoring effect and evaluated negotiations using not only an objective metric but also a subjective metric. Experimental results show that LLMs are influenced by the anchoring effect like humans. Additionally, we investigated the relationship between the anchoring effect and factors such as reasoning and personality. It was shown that reasoning models are less prone to the anchoring effect, suggesting that the long chain of thought mitigates the effect. However, we found no significant correlation between personality traits and susceptibility to the anchoring effect. These findings contribute to a deeper understanding of cognitive biases in LLMs and to the realization of safe and responsible application of LLMs in society.
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。