[论文] teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis...

论文概要

研究领域: ML 作者: Qiwei Li, Jorge Ortiz 发布时间: 2025-07-16 arXiv: 2507.12510

中文摘要

交通管理部门如今拥有大量视频数据用于研究安全性和拥堵问题。然而这些数据多为观察性数据，未经干预收集，这使得诸如降雨如何影响交通密度之类的因果问题难以回答。本文提出 teLLMe——一个面向城市驾驶数据集的探索性因果分析系统。该系统从行车记录仪标注构建的结构化事件表出发，结合因果结构学习（PC算法）、基于自助法的稳定性检验，以及利用线性回归和 DoWhy 进行查询特定效应估计。通过模式感知的大语言模型，自然语言问题被映射为结构化因果查询，使用户能够指定处理变量、结果变量和子人群。teLLMe 返回一张因果卡片，总结效应估计、调整集、DAG 支持度和假设，并附上简短的自然语言解释。基于 BDD 交通事件的案例研究表明，该系统能够揭示涉及天气、高峰时段和交通密度的合理关联，同时显式呈现不确定性和建模选择。该系统定位为假设生成和专家推理工具，而非确定性因果结论的来源。

原文摘要

Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion. Most of these data are observational and collected without interventions, which makes causal questions such as How would rain change traffic density? difficult to answer. We present teLLMe, a system for exploratory causal analysis of urban driving datasets. The system starts from a structured event table built from dashcam annotations and combines causal structure learning with the PC algorithm, bootstrap-based stability checks, and query-specific effect estimation using linear regression and DoWhy. Natural-language questions are mapped to structured causal queries through a schema-aware LLM, enabling users to specify treatments, outcomes, and subpopulations. teLLMe returns a Causal Card that summarizes effect estimates, adjustment sets, DAG support, and assumptions, followed by a ...

--- *自动采集于 2026-07-19*

#论文 #arXiv #ML #小凯