Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds

TL;DR

The paper introduces the Causal Cartographer framework, which extracts causal knowledge and enhances large language models' ability to perform reliable counterfactual reasoning by constructing causal networks and constrained inference agents.

Contribution

It presents a novel framework combining causal relationship extraction with reasoning agents to improve counterfactual reasoning in large language models.

Findings

Extracted large networks of real-world causal relationships.

Improved robustness of LLMs in causal reasoning tasks.

Reduced inference costs and spurious correlations.

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. It requires understanding the underlying causes behind chains of events and conducting causal inference for arbitrary unseen distributions. So far, this task eludes foundation models, notably 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 explicitly extracting and modeling causal relationships and propose the Causal Cartographer framework. First, we introduce a graph retrieval-augmented generation agent tasked to retrieve causal relationships from data. This approach allows us to construct a large network of real-world causal relationships that can serve as a repository of causal knowledge and build real-world counterfactuals. In addition, we create a counterfactual reasoning agent constrained by causal relationships to perform reliable step-by-step causal inference. We show that our approach can extract causal knowledge and improve the robustness of LLMs for causal reasoning tasks while reducing inference costs and spurious correlations.