# Can LLMs Leverage Observational Data? Towards Data-Driven Causal Discovery with LLMs

arXiv: https://arxiv.org/abs/2504.10936 · HTML: https://mlsanity.com/paper/2504.10936/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Builds on (most cited first, 12 of 12)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Causal-learn: Causal Discovery in Python](https://mlsanity.com/paper/2307.16405/) (2023)
- [Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation](https://mlsanity.com/paper/2305.07375/) (2023)
- [Integrating Large Language Model for Improved Causal Discovery](https://mlsanity.com/paper/2306.16902/) (2023)
- [Understanding Causality with Large Language Models: Feasibility and Opportunities](https://mlsanity.com/paper/2304.05524/) (2023)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosis](https://mlsanity.com/paper/2301.13819/) (2023)
- [Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach](https://mlsanity.com/paper/2402.01454/) (2024)
- [MIMICause: Representation and automatic extraction of causal relation types from clinical notes](https://mlsanity.com/paper/2110.07090/) (2021)
- [Prompting or Fine-tuning? Exploring Large Language Models for Causal Graph Validation](https://mlsanity.com/paper/2406.16899/) (2024)
- [Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery](https://mlsanity.com/paper/2407.18752/) (2024)

## Built on by (most cited first, 5 of 5)

- [LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery](https://mlsanity.com/paper/2506.00844/) (2025)
- [Bayesian Network Structure Discovery Using Large Language Models](https://mlsanity.com/paper/2511.00574/) (2025)
- [Sequential Causal Discovery with Noisy Language Model Priors](https://mlsanity.com/paper/2506.16234/) (2025)
- [Stability as a Liability:Systematic Breakdown of Linguistic Structure in LLMs](https://mlsanity.com/paper/2601.18588/) (2026)
- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)

## Abstract (arXiv)

Causal discovery traditionally relies on statistical methods applied to observational data, often requiring large datasets and assumptions about underlying causal structures. Recent advancements in Large Language Models (LLMs) have introduced new possibilities for causal discovery by providing domain expert knowledge. However, it remains unclear whether LLMs can effectively process observational data for causal discovery. In this work, we explore the potential of LLMs for data-driven causal discovery by integrating observational data for LLM-based reasoning. Specifically, we examine whether LLMs can effectively utilize observational data through two prompting strategies: pairwise prompting and breadth first search (BFS)-based prompting. In both approaches, we incorporate the observational data directly into the prompt to assess LLMs' ability to infer causal relationships from such data. Experiments on benchmark datasets show that incorporating observational data enhances causal discovery, boosting F1 scores by up to 0.11 point using both pairwise and BFS LLM-based prompting, while outperforming traditional statistical causal discovery baseline by up to 0.52 points. Our findings highlight the potential and limitations of LLMs for data-driven causal discovery, demonstrating their ability to move beyond textual metadata and effectively interpret and utilize observational data for more informed causal reasoning. Our studies lays the groundwork for future advancements toward fully LLM-driven causal discovery.