4arXiv cs.AI (Artificial Intelligence)·
teLLMe: LLM-powered exploratory causal analysis system for urban driving data
Researchers introduce teLLMe, a system that combines causal structure learning (PC algorithm, DoWhy) with a schema-aware LLM to answer natural-language causal queries over urban driving datasets derived from dashcam annotations. Users pose questions like 'How would rain change traffic density?' and receive a structured 'Causal Card' summarizing effect estimates, adjustment sets, DAG support, and uncertainty. Case studies on BDD-derived traffic events demonstrate plausible causal relationships involving weather and peak hours. The system is framed as a hypothesis-generation tool rather than a definitive causal inference engine.
Related guides (1)
Related events (8)
DKCD: Domain knowledge-enhanced causal discovery from unstructured data using LLMs
Researchers introduce DKCD, a framework that augments LLM-based causal discovery with domain-specific knowledge retrieval and guided reasoning to address two failure modes: insufficient identification of latent causal factors and unreliable factor annotation. The system chains knowledge mining, knowledge-guided causal reasoning, and causal structure discovery into a pipeline that produces causal graphs from unstructured text in high-expertise domains like healthcare and finance. Experiments on two domain-specific datasets show improvements over baselines on both factor identification and graph construction quality.
Study compares human and LLM active causal reasoning, finding LLMs less efficient but near human-level on conjunctive rules
A new arXiv paper investigates whether active exploration reduces the 'conjunctive handicap' in causal learning, using a blicket detector task with adult participants who could freely intervene to identify causal objects. Results show active exploration substantially improves human conjunctive causal reasoning, though conjunctive rules still require more tests than disjunctive ones. State-of-the-art LLMs approach human-level hypothesis inference accuracy but show less efficient exploration strategies and similar conjunctive-disjunctive performance gaps, raising questions about the nature of LLM causal reasoning.
CausaLab: Scalable Benchmark for Interactive Causal Discovery by LLM Agents
CausaLab is a new evaluation environment that tests LLM agents on interactive causal discovery tasks, requiring them to recover both causal graphs and structural equations from synthetic laboratory episodes governed by randomly sampled structural causal models (SCMs). The benchmark separates predictive accuracy from genuine causal understanding, revealing a persistent gap: GPT-5.2-high achieves 92% task accuracy in a 6-node observational setting but only 0.471 all-edge F1 for mechanism recovery. Mixed observation-intervention strategies improve structural fidelity, while pure intervention strategies underperform on both metrics. Premature stopping is identified as a key agent weakness, partially mitigated by prompting models to verify hypothesis-data consistency.
Paper argues LLMs learn causal structure via difference-making logic, not Pearl/Rubin frameworks
A new arXiv preprint proposes that LLMs learn causal structure through 'variational induction' — a difference-making logic — rather than through the dominant formalisms of Judea Pearl's interventionist approach or the Neyman-Rubin potential outcomes framework. The author analyzes how this logic is realized during training and maps specific architectural features (token embeddings, self-attention) to their roles in this inductive process. The argument draws a parallel between LLM causal learning and the experimental method of systematically varying circumstances. This is a theoretical contribution to understanding how LLMs represent causal and world-model structure.
Causal evaluation framework for learnability of formal language tasks in LMs
A new arXiv preprint proposes a causal framework for evaluating how much task-specific data language models need to learn a given task. The authors use formal languages generated by probabilistic finite automata as a controlled testbed, introducing the 'binning semiring' algebraic object to control property frequency in training corpora. Experiments show that standard correlational evaluation practices produce incorrect learnability conclusions due to confounders, with implications for how natural-language task learning is studied.
Study finds shared pattern-matching mechanisms underlie both human and LLM everyday reasoning errors
A new arXiv paper evaluates human participants and 25 LLMs on commonsense causal reasoning tasks, finding similar error patterns in both groups. The authors identify specific attention heads driving LLM responses that implement pattern-matching, and show these heads can predict human reasoning errors caused by superficially irrelevant prompt details. The findings challenge the common assumption that human reasoning relies on principled abstract world models while LLMs merely pattern-match, suggesting both may share a more unified cognitive mechanism.
LLMs reproduce human behavioral biases in route choice without explicit prospect-theoretic parameters
A new arXiv preprint investigates whether LLMs can replicate systematic human decision-making biases in route choice scenarios without explicitly specifying cumulative prospect theory (CPT) parameters. The authors design a behavioral evaluation framework and find that LLMs reproduce non-rational choice patterns consistent with CPT effects under uncertainty. The findings suggest LLMs could serve as a scalable substitute for survey-based parameter calibration in agent-based behavioral simulations, addressing a longstanding bottleneck in large-scale human decision modeling.
CARLA-GS: Modular pipeline for photorealistic autonomous driving corner-case synthesis using LLMs and Gaussian splatting
CARLA-GS is a new modular framework for synthesizing safety-critical corner cases for autonomous driving evaluation, decoupling visual representation (editable Gaussian scenes), semantic reasoning (multi-agent LLM for waypoint generation), and physics simulation (CARLA with PID control). The pipeline reconstructs real driving scenes from the Waymo Open Dataset, uses LLMs to identify risky interactions and generate intent-level trajectories, then re-projects simulated states into Gaussian scenes for photorealistic ego-centric rendering. The approach addresses a key gap in AV safety evaluation: generating spatiotemporally consistent, physically feasible, and semantically meaningful rare scenarios at scale.