CausalChat：使用大型语言模型的交互式因果模型开发与精化
CausalChat: Interactive Causal Model Development and Refinement Using Large Language Models
AI总结：
CausalChat利用GPT-4等大型语言模型中的因果知识，通过对话式可视分析界面帮助用户递归探索变量关系，构建和精化因果网络，并通过用户研究验证其有效性。
摘要：
因果网络在许多领域被广泛用于建模变量之间的复杂关系。最近的一种方法试图通过人类的集体参与来利用群体智慧构建因果网络。虽然这种方法可以产生相当好地建模潜在现象的详细因果网络，但它需要大量具有领域理解能力的个体。我们采用一种不同的方法：利用大型语言模型（如OpenAI的GPT-4）通过摄取大量文献所学到的因果知识。在一个名为CausalChat的专用可视分析界面中，用户递归地探索单个变量或变量对，以识别因果关系、潜在变量、混杂因素和中介变量，通过对话构建详细的因果网络。每次探测交互都被转换为定制的GPT-4提示，响应通过视觉表示传达，并与生成的文本相链接以进行解释。我们在不同的数据情境下展示了CausalChat的功能，并进行了涉及领域专家和非专业人士的用户研究。
英文摘要：
Causal networks are widely used in many fields to model the complex relationships between variables. A recent approach has sought to construct causal networks by leveraging the wisdom of crowds through the collective participation of humans. While this can yield detailed causal networks that model the underlying phenomena quite well, it requires a large number of individuals with domain understanding. We adopt a different approach: leveraging the causal knowledge that large language models, such as OpenAI's GPT-4, have learned by ingesting massive amounts of literature. Within a dedicated visual analytics interface, called CausalChat, users explore single variables or variable pairs recursively to identify causal relations, latent variables, confounders, and mediators, constructing detailed causal networks through conversation. Each probing interaction is translated into a tailored GPT-4 prompt and the response is conveyed through visual representations which are linked to the generated text for explanations. We demonstrate the functionality of CausalChat across diverse data contexts and conduct user studies involving both domain experts and laypersons.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
