# Structured Thinking Matters: Improving LLMs Generalization in Causal Inference Tasks

arXiv: https://arxiv.org/abs/2505.18034 · HTML: https://mlsanity.com/paper/2505.18034/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 3 of its 15 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 3 of 3)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [TALM: Tool Augmented Language Models](https://mlsanity.com/paper/2205.12255/) (2022)
- [Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation](https://mlsanity.com/paper/2412.13952/) (2024)

## Built on by (most cited first, 2 of 2)

- [Why LLMs Fail at Causal Discovery and How Interventional Agents Escape](https://mlsanity.com/paper/2605.27567/) (2026)
- [Externalized CPDAG Summaries Improve LLM Causal Deduction](https://mlsanity.com/paper/2609.31071/) (2026)

## Abstract (arXiv)

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.