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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yanming, Kota, Akshith, Papenhausen, Eric, Mueller, Klaus
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917808285155328
author Zhang, Yanming
Kota, Akshith
Papenhausen, Eric
Mueller, Klaus
author_facet Zhang, Yanming
Kota, Akshith
Papenhausen, Eric
Mueller, Klaus
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14146
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CausalChat: Interactive Causal Model Development and Refinement Using Large Language Models
Zhang, Yanming
Kota, Akshith
Papenhausen, Eric
Mueller, Klaus
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Social and Information Networks
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.
title CausalChat: Interactive Causal Model Development and Refinement Using Large Language Models
topic Artificial Intelligence
Human-Computer Interaction
Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2410.14146