用生成式AI分析文本图像数据，无需微调模型即可做因果推断。
Leveraging Generative Artificial Intelligence for Causal Inference with Unstructured Data
- 利用开源生成模型提取文本图像的低维结构化表示
- 在不微调模型下实现因果效应估计与不确定性量化
- 适合研究社会媒体、图像特征、政治话语等领域的学者
我们提出生成式AI驱动的推断框架（GPI），用于处理文本和图像等非结构化数据的因果与预测推断。GPI利用开源生成式人工智能模型（如大语言模型和扩散模型），不仅可大规模生成非结构化数据，还能提取保证捕捉其底层结构的低维表示。基于这些表示进行机器学习，可实现因果效应估计并量化估计不确定性。与现有表示学习方法不同，GPI无需微调生成模型，计算高效且易于使用。我们通过三个应用展示了该框架的通用性：(1) 在调整文本混杂因素的前提下估计中国社交媒体审查的影响；(2) 从同一图像中分离特定视觉特征的独立影响；(3) 评估政治修辞的说服力。相关开源软件包已发布。
原文摘要 · Abstract (English)
We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text and images. GPI leverages open-source Generative Artificial Intelligence (GenAI) models---such as large language models and diffusion models---not only to generate unstructured data at scale but also to extract low-dimensional representations that are guaranteed to capture their underlying structure. Applying machine learning to these representations, GPI enables estimation of causal effects while quantifying associated estimation uncertainty. Unlike existing approaches to representation learning, GPI does not require fine-tuning of generative models, making it computationally efficient and broadly accessible. We illustrate the versatility of the GPI framework through three applications: (1) estimating the effects of Chinese social media censorship while adjusting for textual confounders, (2) isolating the impact of specific image features from that of other correlated features in the same image, and (3) assessing the persuasiveness of political rhetoric. An open-source software package is available for implementing GPI.
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。