# An Explainable AI Approach to Large Language Model Assisted Causal Model Auditing and Development

arXiv: https://arxiv.org/abs/2312.16211 · HTML: https://mlsanity.com/paper/2312.16211/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 23 Dec 2023.

## Builds on (most cited first, 16 of 16)

- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Can large language models build causal graphs?](https://mlsanity.com/paper/2303.05279/) (2023)
- [Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation](https://mlsanity.com/paper/2305.07375/) (2023)
- [Causal Discovery with Language Models as Imperfect Experts](https://mlsanity.com/paper/2307.02390/) (2023)
- [A Survey on Extraction of Causal Relations from Natural Language Text](https://mlsanity.com/paper/2101.06426/) (2021)
- [Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias](https://mlsanity.com/paper/2111.04095/) (2021)
- [An Evaluation Toolkit to Guide Model Selection and Cohort Definition in Causal Inference](https://mlsanity.com/paper/1906.00442/) (2019)
- [D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias](https://mlsanity.com/paper/2208.05126/) (2022)
- [Visual Causality Analysis of Event Sequence Data](https://mlsanity.com/paper/2009.00219/) (2020)
- [Outcome-Explorer: A Causality Guided Interactive Visual Interface for Interpretable Algorithmic Decision Making](https://mlsanity.com/paper/2101.00633/) (2021)
- [A Visual Analytics Approach for Exploratory Causal Analysis: Exploration, Validation, and Applications](https://mlsanity.com/paper/2009.02458/) (2020)
- [Illusion of Causality in Visualized Data](https://mlsanity.com/paper/1908.00215/) (2019)
- [VAINE: Visualization and AI for Natural Experiments](https://mlsanity.com/paper/2109.04348/) (2021)
- [Once Upon A Time In Visualization: Understanding the Use of Textual Narratives for Causality](https://mlsanity.com/paper/2009.02649/) (2020)
- [Causal Support: Modeling Causal Inferences with Visualizations](https://mlsanity.com/paper/2107.13485/) (2021)
- [DOMINO: Visual Causal Reasoning with Time-Dependent Phenomena](https://mlsanity.com/paper/2303.06556/) (2023)

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

- [Navigating LLM Ethics: Advancements, Challenges, and Future Directions](https://mlsanity.com/paper/2406.18841/) (2024)
- [STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond](https://mlsanity.com/paper/2409.05367/) (2024)
- [CausalChat: Interactive Causal Model Development and Refinement Using Large Language Models](https://mlsanity.com/paper/2410.14146/) (2024)
- [Learning to Defer for Causal Discovery with Imperfect Experts](https://mlsanity.com/paper/2502.13132/) (2025)
- [Into the Void: Mapping the Unseen Gaps in High Dimensional Data](https://mlsanity.com/paper/2501.15273/) (2025)

## Abstract (arXiv)

Causal networks are widely used in many fields, including epidemiology, social science, medicine, and engineering, to model the complex relationships between variables. While it can be convenient to algorithmically infer these models directly from observational data, the resulting networks are often plagued with erroneous edges. Auditing and correcting these networks may require domain expertise frequently unavailable to the analyst. We propose the use of large language models such as ChatGPT as an auditor for causal networks. Our method presents ChatGPT with a causal network, one edge at a time, to produce insights about edge directionality, possible confounders, and mediating variables. We ask ChatGPT to reflect on various aspects of each causal link and we then produce visualizations that summarize these viewpoints for the human analyst to direct the edge, gather more data, or test further hypotheses. We envision a system where large language models, automated causal inference, and the human analyst and domain expert work hand in hand as a team to derive holistic and comprehensive causal models for any given case scenario. This paper presents first results obtained with an emerging prototype.