LLM推荐会加剧社会分化，即使模型本身无偏。
Observing Micromotives and Macrobehavior of Large Language Models
- 用谢林模型模拟用户听从LLM建议后的社会演化
- 无论模型是否带偏见，更多人采纳都导致高度社会隔离
- 警示盲目去偏见可能忽略系统性社会影响
托马斯·谢林（Thomas C. Schelling）指出，个体决策（微动机）虽具局部性，却可能引发远超预期的社会结果（宏观行为）。当前关于大语言模型（LLMs）微动机的研究多假设：若消除模型偏好或偏见，用户将做出更优决策，因而大量研究聚焦于去除模型偏见。然而，在自然语言处理领域，尽管对模型微动机有诸多讨论，此前研究极少系统考察模型如何影响社会宏观行为。本文借鉴谢林的隔离模型，观察LLM的微动机与宏观行为之间的关系。结果显示，无论模型偏见程度如何，当越来越多用户采纳LLM建议时，社会将趋向高度隔离。我们希望此研究能引发对“缓解模型微动机”这一基本假设的再思考，并促使重新评估LLM对用户及社会的影响。
原文摘要 · Abstract (English)
Thomas C. Schelling, awarded the 2005 Nobel Memorial Prize in Economic Sciences, pointed out that ``individuals decisions (micromotives), while often personal and localized, can lead to societal outcomes (macrobehavior) that are far more complex and different from what the individuals intended.'' The current research related to large language models' (LLMs') micromotives, such as preferences or biases, assumes that users will make more appropriate decisions once LLMs are devoid of preferences or biases. Consequently, a series of studies has focused on removing bias from LLMs. In the NLP community, while there are many discussions on LLMs' micromotives, previous studies have seldom conducted a systematic examination of how LLMs may influence society's macrobehavior. In this paper, we follow the design of Schelling's model of segregation to observe the relationship between the micromotives and macrobehavior of LLMs. Our results indicate that, regardless of the level of bias in LLMs, a highly segregated society will emerge as more people follow LLMs' suggestions. We hope our discussion will spark further consideration of the fundamental assumption regarding the mitigation of LLMs' micromotives and encourage a reevaluation of how LLMs may influence users and 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。