验证是生成性社会模拟的核心挑战:对基于代理的建模中LLM的批判性审查
Maik Larooij1, Petter Törnberg1
1University of Amsterdam, Amsterdam, The Netherlands.
概括
使用大型语言模型 (LLM) 的基于代理的生成模型 (ABM) 提供了现实性,但也带来了验证挑战. 目前的方法与LLM偏见和黑盒性质作斗争,阻碍了社会科学研究的经验基础.
科学领域:
- 计算社会科学 计算社会科学
- 人工智能的人工智能
背景情况:
- 大型语言模型 (LLM) 能够实现增强现实性的生成代理模型 (ABM).
- 这种重新振兴的兴趣使ABM验证和经验基础的长期挑战重新复活.
研究的目的:
- 系统地审查有关生成型ABM的文献.
- 评估新兴研究中如何解决验证挑战.
- 绘制应用程序域和分类验证实践的地图.
主要方法:
- 系统的文献审查.
- 应用领域的映射.
- 验证实践的分类和评估与建模目标的一致性.
主要成果:
- 使用LLM可能会加剧ABM验证困难,原因是黑子的性质,偏见和随机性.
- 验证实践往往依赖于面值验证或与机制联系较弱的结果措施.
- 认可的验证需求正在增加,但往往不足.
结论:
- 生成型ABM在正式模型和数据驱动模型之间占据了一种方法空间.
- 解决现实主义和实证有效性之间的紧张关系对于累积的社会科学知识至关重要.
- 生成型ABM的贡献取决于解决验证和接地问题的问题.
相关概念视频
Modeling and Similitude
588
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
588
Automatic Processing and Automatic Social Behavior
201
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
201
Language and Cognition
696
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
696
Models, Theories, and Laws
8.2K
Scientists frequently use models to help them comprehend a specific collection of phenomena. In physics, a model is a condensed version of a physical system that is too complex to study thoroughly. One such example is the light wave model; unlike water waves, light waves are typically invisible to us. Nonetheless, it is helpful to think of light as being composed of waves, since investigations show that light behaves like water waves. Since it is impossible to visually see what is genuinely...
8.2K
Mechanistic Models: Compartment Models in Individual and Population Analysis
230
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
230
Social Foundations of Self II: The Generalized Other
219
According to George Herbert Mead, as children progress beyond the game stage, they develop a more comprehensive understanding of societal rules and norms. This cognitive and social development enables them to internalize the expectations of the broader community, refining their ability to regulate behavior.Consistent participation in organized activities is crucial in helping children recognize that their actions are not isolated but contribute to a more significant, interconnected group...
219

