用大模型对话构建因果网络，让普通人也能探索变量间因果关系。
CausalChat: Interactive Causal Model Development and Refinement Using Large Language Models
- 通过对话式交互，让大模型动态生成因果推理提示
- 用户可逐步发现隐变量、混杂因子和中介效应
- 适合非专家在复杂系统中探索因果机制
因果网络广泛应用于多个领域以建模变量间的复杂关系。近期方法尝试通过众包方式集合人类专业知识来构建因果网络，虽能生成细致模型，但需大量具备领域知识的参与者。本文提出新思路：利用大语言模型（如GPT-4）从海量文献中学习到的因果知识。在名为CausalChat的可视化分析界面中，用户可通过递归探索单个变量或变量对，识别因果关系、潜在变量、混杂因子与中介效应，借助与模型的对话逐步构建详细因果网络。每次交互转化为定制化GPT-4提示，结果以视觉形式呈现，并与生成文本关联以提供解释。我们在多种数据场景下验证了CausalChat的功能性，并通过包含领域专家与普通用户的用户研究评估其有效性。
原文摘要 · Abstract (English)
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.
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。