# CausalChat: Interactive Causal Model Development and Refinement Using Large Language Models

arXiv: https://arxiv.org/abs/2410.14146 · HTML: https://mlsanity.com/paper/2410.14146/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 53 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Builds on (most cited first, 18 of 18)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)
- [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)
- [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)
- [A Visual Analytics Approach for Exploratory Causal Analysis: Exploration, Validation, and Applications](https://mlsanity.com/paper/2009.02458/) (2020)
- [Why Would You Suggest That? Human Trust in Language Model Responses](https://mlsanity.com/paper/2406.02018/) (2024)
- [Causalvis: Visualizations for Causal Inference](https://mlsanity.com/paper/2303.00617/) (2023)
- [DOMINO: Visual Causal Reasoning with Time-Dependent Phenomena](https://mlsanity.com/paper/2303.06556/) (2023)
- [An Explainable AI Approach to Large Language Model Assisted Causal Model Auditing and Development](https://mlsanity.com/paper/2312.16211/) (2023)
- [Efficient Crowd Exploration of Large Networks: The Case of Causal Attribution](https://mlsanity.com/paper/1810.03163/) (2018)
- [Belief Miner: A Methodology for Discovering Causal Beliefs and Causal Illusions from General Populations](https://mlsanity.com/paper/2401.08020/) (2024)

## 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)
- [XplainAct: Visualization for Personalized Intervention Insights](https://mlsanity.com/paper/2507.14767/) (2025)
- [No More Maybe-Arrows: Resolving Causal Uncertainty by Breaking Symmetries](https://mlsanity.com/paper/2603.01052/) (2026)

## Abstract (arXiv)

Causal networks are widely used in many fields to model the complex relationships between variables. A recent approach has sought to construct causal networks by leveraging the wisdom of crowds through the collective participation of humans. While this can yield detailed causal networks that model the underlying phenomena quite well, it requires a large number of individuals with domain understanding. We adopt a different approach: leveraging the causal knowledge that large language models, such as OpenAI's GPT-4, have learned by ingesting massive amounts of literature. Within a dedicated visual analytics interface, called CausalChat, users explore single variables or variable pairs recursively to identify causal relations, latent variables, confounders, and mediators, constructing detailed causal networks through conversation. Each probing interaction is translated into a tailored GPT-4 prompt and the response is conveyed through visual representations which are linked to the generated text for explanations. We demonstrate the functionality of CausalChat across diverse data contexts and conduct user studies involving both domain experts and laypersons.