diff --git a/NAMESPACE b/NAMESPACE
index 9ae3ed28..81dd1dd4 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -19,7 +19,6 @@ export(get_perf_metric_name)
 export(get_performance_tbl)
 export(get_tuning_grid)
 export(group_correlated_features)
-export(keep_groups_in_cv_partitions)
 export(plot_hp_performance)
 export(plot_model_performance)
 export(preprocess_data)
diff --git a/R/cross_val.R b/R/cross_val.R
index 4b1ff605..f1c4f535 100644
--- a/R/cross_val.R
+++ b/R/cross_val.R
@@ -93,7 +93,7 @@ get_seeds_trainControl <- function(hyperparams_list, kfold, cv_times, ncol_train
 #' @inheritParams define_cv
 #'
 #' @return `TRUE` if possible, `FALSE` otherwise
-#' @export
+#' @noRd
 #' @author Kelly Sovacool, \email{sovacool@@umich.edu}
 #'
 keep_groups_in_cv_partitions <- function(groups, group_partitions, kfold) {
diff --git a/man/keep_groups_in_cv_partitions.Rd b/man/keep_groups_in_cv_partitions.Rd
deleted file mode 100644
index c54254d3..00000000
--- a/man/keep_groups_in_cv_partitions.Rd
+++ /dev/null
@@ -1,36 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/cross_val.R
-\name{keep_groups_in_cv_partitions}
-\alias{keep_groups_in_cv_partitions}
-\title{Whether groups can be kept together in partitions during cross-validation}
-\usage{
-keep_groups_in_cv_partitions(groups, group_partitions, kfold)
-}
-\arguments{
-\item{groups}{Vector of groups to keep together when splitting the data into
-train and test sets. If the number of groups in the training set is larger
-than \code{kfold}, the groups will also be kept together for cross-validation.
-Length matches the number of rows in the dataset (default: \code{NULL}).}
-
-\item{group_partitions}{Specify how to assign \code{groups} to the training and
-testing partitions (default: \code{NULL}). If \code{groups} specifies that some
-samples belong to group \code{"A"} and some belong to group \code{"B"}, then setting
-\code{group_partitions = list(train = c("A", "B"), test = c("B"))} will result
-in all samples from group \code{"A"} being placed in the training set, some
-samples from \code{"B"} also in the training set, and the remaining samples from
-\code{"B"} in the testing set. The partition sizes will be as close to
-\code{training_frac} as possible. If the number of groups in the training set is
-larger than \code{kfold}, the groups will also be kept together for
-cross-validation.}
-
-\item{kfold}{Fold number for k-fold cross-validation (default: \code{5}).}
-}
-\value{
-\code{TRUE} if possible, \code{FALSE} otherwise
-}
-\description{
-Whether groups can be kept together in partitions during cross-validation
-}
-\author{
-Kelly Sovacool, \email{sovacool@umich.edu}
-}