[论文] teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data

论文概要

研究领域: cs.AI, cs.HC 作者: Qiwei Li, Jorge Ortiz 发布时间: 2026-07-16 arXiv: 2607.15254

中文摘要

交通管理部门现在可以获取大量从视频提取的数据用于研究安全和拥堵问题。但这些数据大多是观察性的，且在没有干预的情况下收集，这使得因果问题（如雨天会如何改变交通密度？）难以回答。本文提出 teLLMe，一个面向城市驾驶数据集的可探索性因果分析系统。系统从行车记录仪标注构建结构化事件表出发，结合基于 PC 算法的因果结构学习、基于 Bootstrap 的稳定性检验，以及使用线性回归和 DoWhy 的查询特定效应估计。自然语言问题通过模式感知的 LLM 映射为结构化因果查询，用户可以指定处理变量、结果变量和子人群。teLLMe 返回一张因果卡片，汇总效应估计、调整集、DAG 支撑和假设，随后给出简短的自然语言解释。基于 BDD 交通事件的案例研究表明，该系统能够呈现涉及天气、高峰时段和交通密度之间的合理关系，同时显式地表达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，而非确定性因果声明的来源。

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 short natural-language explanation. Case studies on BDD-derived traffic events show that the system can surface plausible relationships involving weather, peak hours, and traffic density, while making uncertainty and modeling choices explicit. The system is designed as a tool for hypothesis generation and expert reasoning rather than a source of definitive causal claims.

--- *自动采集于 2026-07-20*

#论文 #arXiv #AI #小凯