# Using GPT-4 to guide causal machine learning

arXiv: https://arxiv.org/abs/2407.18607 · HTML: https://mlsanity.com/paper/2407.18607/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 7 of 7)

- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [Can Large Language Models Infer Causation from Correlation?](https://mlsanity.com/paper/2306.05836/) (2023)
- [A survey of Bayesian Network structure learning](https://mlsanity.com/paper/2109.11415/) (2021)
- [Understanding Causality with Large Language Models: Feasibility and Opportunities](https://mlsanity.com/paper/2304.05524/) (2023)
- [The impact of prior knowledge on causal structure learning](https://mlsanity.com/paper/2102.00473/) (2021)
- [Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach](https://mlsanity.com/paper/2402.01454/) (2024)
- [Open problems in causal structure learning: A case study of COVID-19 in the UK](https://mlsanity.com/paper/2305.03859/) (2023)

## Built on by (most cited first, 3 of 3)

- [LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery](https://mlsanity.com/paper/2506.00844/) (2025)
- [Guide: Generalized-Prior and Data Encoders for DAG Estimation](https://mlsanity.com/paper/2509.23992/) (2025)
- [LLM-Augmented Causal Discovery: Probabilistic Fusion of Edge Existence and Orientation](https://mlsanity.com/paper/2608.27472/) (2026)

## Abstract (arXiv)

Since its introduction to the public, ChatGPT has had an unprecedented impact. While some experts praised AI advancements and highlighted their potential risks, others have been critical about the accuracy and usefulness of Large Language Models (LLMs). In this paper, we are interested in the ability of LLMs to identify causal relationships. We focus on the well-established GPT-4 (Turbo) and evaluate its performance under the most restrictive conditions, by isolating its ability to infer causal relationships based solely on the variable labels without being given any other context by humans, demonstrating the minimum level of effectiveness one can expect when it is provided with label-only information. We show that questionnaire participants judge the GPT-4 graphs as the most accurate in the evaluated categories, closely followed by knowledge graphs constructed by domain experts, with causal Machine Learning (ML) far behind. We use these results to highlight the important limitation of causal ML, which often produces causal graphs that violate common sense, affecting trust in them. However, we show that pairing GPT-4 with causal ML overcomes this limitation, resulting in graphical structures learnt from real data that align more closely with those identified by domain experts, compared to structures learnt by causal ML alone. Overall, our findings suggest that despite GPT-4 not being explicitly designed to reason causally, it can still be a valuable tool for causal representation, as it improves the causal discovery process of causal ML algorithms that are designed to do just that.