Package: Gtheory4LLM
Type: Package
Title: Generalizability Theory for LLM Subjective Tasks
Version: 0.2.0
Authors@R: person("Jin", "Liu", email = "Veronica.Liu0206@gmail.com",
    role = c("aut", "cre", "cph"))
Author: Jin Liu [aut, cre, cph]
Maintainer: Jin Liu <Veronica.Liu0206@gmail.com>
Description: Studies the reliability and generalizability of subjective
    judgments produced by large language models (LLMs), including annotation,
    rating, and structured LLM-as-a-judge tasks. Specifies evaluator, prompt,
    generation, and repeated-run facets through crossed or explicitly nested
    random sources with configurable item interactions. Fits univariate models,
    joint Gaussian models, and joint discrete models for binary, ordinal, and
    unordered categorical outcomes, with source-specific covariance. Gaussian
    models use exact balanced likelihood; discrete models use a dense
    first-order Laplace approximation with Gaussian latent random effects.
    Supported balanced decision studies compare evaluator, prompt, and
    replication allocations using observed Gaussian or explicitly requested
    latent binary and ordinal reliability, with random or fixed facets after
    Brennan (2001). Gaussian fits report asymptotic Wald standard errors for
    their variance components and delta-method intervals for the coefficients;
    discrete fits report point estimates only. Scalar nominal reliability and
    joint Gaussian-discrete fitting are not implemented. Includes three publicly
    archived LLM annotation datasets covering hate-speech, mental-health,
    and drug-review tasks. Discrete fitting is limited to small models; the
    preflight report describes supported designs and computational limits.
    Generalizability coefficients follow the variance-decomposition framework
    of Brennan (2001) <doi:10.1007/978-1-4757-3456-0>.
License: GPL-3
Encoding: UTF-8
Depends: R (>= 4.5.0)
Imports: Matrix (>= 1.6.0), OpenMx (>= 2.22.11), graphics, methods,
        stats, utils
Suggests: lme4, ordinal, knitr, rmarkdown
VignetteBuilder: knitr
URL: https://github.com/Veronica0206/Gtheory4LLM
BugReports: https://github.com/Veronica0206/Gtheory4LLM/issues
Collate: 'design.R' 'family.R' 'gaussian_retry.R' 'gaussian_engine.R'
        'gaussian.R' 'discrete_response.R' 'discrete_dense.R'
        'discrete_sparse.R' 'discrete_mode.R' 'discrete_sparse_mode.R'
        'discrete.R' 'preflight.R' 'diagnostics_stages.R' 'fit.R'
        'methods.R' 'reliability.R' 'examples.R'
NeedsCompilation: no
Packaged: 2026-09-23 03:32:10 UTC; runner
Repository: CRAN
Date/Publication: 2026-10-04 09:30:02 UTC
Built: R 4.6.1; ; 2026-10-04 11:37:27 UTC; unix
