Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds

ICLR 2026 Conference Submission14563 Authors

Keywords: Large Language Models, Retrieval-Augmented Generation, Causal Extration, Causal Inference, Counterfactual reasoning, Evaluation, Efficiency

TL;DR: We introduce a framework extracting causal world knowledge and using it as causal constraints for counterfactual reasoning. We show that it allows building consistent causal world models and improves efficiency in real-world counterfactual inference.

Abstract: Causal world models are systems that can answer counterfactual questions about an environment of interest, i.e., predict how it would have evolved if an arbitrary subset of events had been realized differently. The ability to answer such questions is crucial for models to reliably understand the world. However, this task currently eludes large language models (LLMs), which do not have demonstrated causal reasoning capabilities beyond the memorization of existing causal relationships. Furthermore, evaluating counterfactuals in real-world applications is challenging since only the factual world is observed, limiting evaluation to synthetic datasets. We address these problems by proposing the Causal Cartographer, a twofold system composed of two agents: the first extracts causal relationships from data and builds a vast repository of causal knowledge, while the second uses them as constraints to perform reliable step-by-step causal inference. We evaluate our approach on real-world counterfactuals obtained by matching data from diverse news sources. We show that our approach can extract accurate causal knowledge and enhance the robustness of LLMs for causal reasoning tasks. In particular, the proposed causal conditioning mitigates the impact of spurious correlations and greatly reduces inference costs (by up to 70\%) compared to chain-of-thought reasoning.

Primary Area: causal reasoning

Submission Number: 14563