Package: Gtheory4LLM
Type: Package
Title: Generalizability Theory for LLM Subjective Tasks
Version: 1.0.0
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, with a bounded observed-row route
    for incomplete univariate panels. Discrete models use dense or sparse
    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). 'OpenMx' Gaussian fits report asymptotic Wald standard errors
    for variance components and delta-method coefficient intervals when
    curvature checks permit them; the 'lme4' route returns point estimates only.
    Discrete fits offer optional full-information latent coefficient intervals,
    subject to numerical and boundary checks. An object bootstrap refits
    resampled objects under each fit's acceptance rule and gives percentile and
    bias-corrected and accelerated intervals for components, coefficients and
    decision studies. Provides fixed-layout call
    effects, categorical score and category-vector reliability projections,
    repeated-panel decision agreement, bounded cost-aware comparisons, and
    Gaussian or latent binary/ordinal pilot precision planning, and categorical
    point-estimator pilot operating characteristics. Joint
    Gaussian-discrete fitting is not implemented. Includes three publicly
    archived LLM annotation datasets covering hate-speech, mental-health,
    and drug-review tasks. Discrete fitting retains conservative size limits;
    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,
        parallel, stats, tools, utils
Suggests: lme4, ordinal, knitr, rmarkdown
VignetteBuilder: knitr
URL: https://github.com/Veronica0206/Gtheory4LLM
BugReports: https://github.com/Veronica0206/Gtheory4LLM/issues
Collate: 'design.R' 'batch.R' 'family.R' 'gaussian_retry.R'
        'gaussian_initializer.R' 'gaussian_engine.R'
        'gaussian_observed.R' 'gaussian.R' 'gaussian_lme4.R'
        'discrete_response.R' 'discrete_dense.R' 'discrete_sparse.R'
        'selected_inverse.R' 'discrete_sparse_envelope.R'
        'discrete_gradient.R' 'discrete_boundary_escape.R'
        'discrete_mode.R' 'discrete_sparse_mode.R' 'discrete.R'
        'discrete_check.R' 'discrete_information.R' 'preflight.R'
        'diagnostics_stages.R' 'fit.R' 'methods.R' 'reliability.R'
        'batch_reliability.R' 'planning.R' 'simulation.R' 'bootstrap.R'
        'discrete_simulation.R' 'categorical_targets.R'
        'visualization.R' 'report.R' 'examples.R'
NeedsCompilation: yes
Packaged: 2026-11-01 19:09:31 UTC; runner
Repository: CRAN
Date/Publication: 2026-11-01 23:20:21 UTC
