PulseAugur
EN
LIVE 12:09:02

New system teLLMe aids causal analysis of urban driving data

By PulseAugur Editorial · [2 sources] ·

Researchers have developed teLLMe, a system designed for exploratory causal analysis of urban driving data. This system leverages a schema-aware LLM to translate natural-language questions about traffic events into structured causal queries. teLLMe then employs causal structure learning, bootstrap-based stability checks, and estimation techniques to provide a "Causal Card" detailing effect estimates, assumptions, and a natural-language explanation. The tool aims to aid hypothesis generation for traffic agencies by making uncertainty and modeling choices explicit, rather than providing definitive causal claims. AI

IMPACT Enables more sophisticated hypothesis generation for urban planning and traffic safety analysis.

RANK_REASON The cluster describes a research paper detailing a new system for causal analysis.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New system teLLMe aids causal analysis of urban driving data

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Qiwei Li, Jorge Ortiz ·

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

    arXiv:2607.15254v1 Announce Type: new Abstract: 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 ra…

  2. arXiv cs.AI TIER_1 English(EN) · Jorge Ortiz ·

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

    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.…

RELATED ENTITIES

RELATED TOPICS