compute_confusion_matrices

Compute confusion matrices from multi-model annotations

Provides R bindings to the 'llama.cpp' library for running large language models.
The package uses a lightweight architecture where the C++ backend library is downloaded
at runtime rather than bundled with the package.
Package features include text generation, reproducible generation, and parallel inference.

Yaosheng Xu

localLLM

Running Local LLMs with 'llama.cpp' Backend

Eddie Yang

compute_confusion_matrices function

<dl><dt>annotations</dt>
<dd>Output from [explore()] or a compatible data
frame with at least `sample_id`, `model_id`, and `label` columns.</dd>
<dt>gold</dt>
<dd>Optional vector of gold labels. Overrides the `truth` column when
supplied.</dd>
<dt>pairwise</dt>
<dd>When `TRUE`, cross-model confusion tables are returned even
if no gold labels exist.</dd>
<dt>label_levels</dt>
<dd>Optional factor levels to enforce a consistent ordering
in the resulting tables.</dd>
<dt>sample_col, model_col, label_col, truth_col</dt>
<dd>Column names to use when
`annotations` is a custom data frame.</dd></dl>

Arguments

Compute confusion matrices from multi-model annotations — compute_confusion_matrices

<dl>

<dt>annotations</dt>
<dd>Output from [explore()] or a compatible data
frame with at least `sample_id`, `model_id`, and `label` columns.</dd>


<dt>gold</dt>
<dd>Optional vector of gold labels. Overrides the `truth` column when
supplied.</dd>


<dt>pairwise</dt>
<dd>When `TRUE`, cross-model confusion tables are returned even
if no gold labels exist.</dd>


<dt>label_levels</dt>
<dd>Optional factor levels to enforce a consistent ordering
in the resulting tables.</dd>


<dt>sample_col, model_col, label_col, truth_col</dt>
<dd>Column names to use when
`annotations` is a custom data frame.</dd>

</dl>

compute_confusion_matrices: Compute confusion matrices from multi-model annotations

Description

Usage

Value

Arguments