Structured Thinking Matters: Improving LLMs Generalization in Causal Inference Tasks

TL;DR

This paper introduces a structured knowledge graph approach to improve large language models' ability to distinguish causation from correlation, significantly enhancing their performance on causal inference benchmarks.

Contribution

The paper proposes a novel method that guides LLMs to build structured knowledge graphs, improving causal reasoning beyond traditional prompting techniques.

Findings

F1 score improved from 32.71 to 48.26 on Corr2Cause benchmark

Significant gains in precision and recall observed

Method demonstrates potential for broader causal inference tasks

Abstract

Despite remarkable advances in the field, LLMs remain unreliable in distinguishing causation from correlation. Recent results from the Corr2Cause dataset benchmark reveal that state-of-the-art LLMs -- such as GPT-4 (F1 score: 29.08) -- only marginally outperform random baselines (Random Uniform, F1 score: 20.38), indicating limited capacity of generalization. To tackle this limitation, we propose a novel structured approach: rather than directly answering causal queries, we provide the model with the capability to structure its thinking by guiding the model to build a structured knowledge graph, systematically encoding the provided correlational premises, to answer the causal queries. This intermediate representation significantly enhances the model's causal capabilities. Experiments on the test subset of the Corr2Cause dataset benchmark with Qwen3-32B model (reasoning model) show substantial gains over standard direct prompting methods, improving F1 scores from 32.71 to 48.26 (over 47.5% relative increase), along with notable improvements in precision and recall. These results underscore the effectiveness of providing the model with the capability to structure its thinking and highlight its promising potential for broader generalization across diverse causal inference tasks.