ElicitationWizard
0.1.0LLM-Based Bayesian Prior Elicitation Wizard
Overview
'Shiny' application for eliciting Bayesian prior distributions using large language models (LLMs). Supports multiple LLM experts, linear opinion pooling, and the Delphi method for iterative consensus. For more details see J. R. Falconer et al. (2022) doi:10.1287/deca.2022.0451 and D. Selby et al. (2025) doi:10.1002/sta4.70054.
- Initial CRAN release.
- Shiny application for LLM-based Bayesian prior elicitation.
- Supports up to 4 parallel LLM experts with configurable models and temperatures.
- Linear opinion pooling and Delphi iterative consensus methods.
- Stan code generation from elicited priors.
- 15 supported distribution families: Normal, Log-Normal, Beta, Gamma, Exponential, Half-Normal, Cauchy, Half-Cauchy, Uniform, Weibull, Poisson, Student-t, Inverse-Gamma, Log-Logistic, Pareto.
From NEWS.md in the release
Install
Health
- OK13 OK2026-08-05
- NOTE12 OK, 1 NOTE2026-08-01
- OK7 OK2026-05-30
Documentation
- Help pages
- 1
- Examples that run
- 100%1 run in a plain check (under a condition)
- Exported functions with examples
- 100%
- Documented parameters
- not tracked
- Return-value docs
- 100%
- Help pages citing references
- 0%
Downloads
Repository
1 development-tooling and community-health practice detected across 1 family in the upstream repository
Checks run against github.com/jefferyayiti/automated_elicitation on 2026-10-11.
Dependencies
Code & Tests
People & History
- 0.1.0Latest2026-05-29 · current release
- RR 4.6.0 released · 2026-04-24
Package metadata
- First published
- 2026-05-29
- Total releases
- 1 / 1 yrs
- License
- MIT + file LICENSE OSI
- Download size
- 49 KB
Cite
Cite this package
Run in R for the authors' preferred citation:
citation("ElicitationWizard")This package has no citation file, so citation() returns this entry built from DESCRIPTION.
Cite the R Observatory
For a number measured here: a download total, a coverage figure, an archival date.
From data release v2026-10-17, which the citation names so these numbers can be found later. More on citing and the projects behind them.