diff --git a/python/cuml/cuml/internals/array.py b/python/cuml/cuml/internals/array.py
index 4027b31d82..b111bce537 100644
--- a/python/cuml/cuml/internals/array.py
+++ b/python/cuml/cuml/internals/array.py
@@ -983,12 +983,12 @@ def from_input(
 
         if is_sparse(X):
             # We don't support coercing sparse arrays to dense via this method.
-            # Raising a NotImplementedError here lets us nicely error
-            # for estimators that don't support sparse arrays without requiring
-            # an additional external check. Otherwise they'd get an opaque error
-            # for code below.
-            raise NotImplementedError(
-                "Sparse inputs are not currently supported for this method"
+            # Raising a TypeError here lets us nicely error for estimators that
+            # don't support sparse arrays without requiring an additional
+            # external check. Using TypeError with "sparse" in the message
+            # satisfies sklearn's check_estimator_sparse_tag check.
+            raise TypeError(
+                "A sparse matrix was passed, but dense data is required. "
             )
         if convert_to_mem_type is not False:
             convert_to_mem_type = MemoryType.from_str(convert_to_mem_type)
diff --git a/python/cuml/tests/test_exceptions.py b/python/cuml/tests/test_exceptions.py
index fc8d520fca..c4d45cd392 100644
--- a/python/cuml/tests/test_exceptions.py
+++ b/python/cuml/tests/test_exceptions.py
@@ -1,5 +1,5 @@
 #
-# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 #
 
@@ -24,7 +24,7 @@
     NearestNeighbors,
 )
 
-# Currently only certain estimators raise a NotImplementedError
+# Estimators that raise TypeError when given sparse input (they don't support sparse)
 estimators = {
     "KMeans": lambda: KMeans(n_clusters=2, random_state=0),
     "DBSCAN": lambda: DBSCAN(eps=1.0),
@@ -44,7 +44,7 @@ def test_sparse_not_implemented_exception(estimator_name):
     y_reg = np.array([0.0, 1.0])
     estimator = estimators[estimator_name]()
     # Fit or fit_transform depending on the estimator type
-    with pytest.raises(NotImplementedError):
+    with pytest.raises(TypeError, match="sparse"):
         if isinstance(
             estimator, (KMeans, DBSCAN, TruncatedSVD, NearestNeighbors)
         ):
diff --git a/python/cuml/tests/test_sklearn_compatibility.py b/python/cuml/tests/test_sklearn_compatibility.py
index 97156680b7..e88b18f500 100644
--- a/python/cuml/tests/test_sklearn_compatibility.py
+++ b/python/cuml/tests/test_sklearn_compatibility.py
@@ -56,9 +56,6 @@
         "check_complex_data": "KMeans does not handle complex data",
         "check_dtype_object": "KMeans does not handle object dtype",
         "check_estimators_nan_inf": "KMeans does not check for NaN and inf",
-        "check_estimator_sparse_tag": "KMeans does not support sparse data",
-        "check_estimator_sparse_array": "KMeans does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "KMeans does not handle sparse matrices gracefully",
         "check_transformer_data_not_an_array": "KMeans does not handle non-array data",
         "check_fit1d": "KMeans does not raise ValueError for 1D input",
         "check_fit2d_predict1d": "KMeans does not handle 1D prediction input gracefully",
@@ -74,9 +71,6 @@
         "check_dtype_object": "KernelRidge does not handle object dtype",
         "check_estimators_empty_data_messages": "KernelRidge does not handle empty data",
         "check_estimators_nan_inf": "KernelRidge does not check for NaN and inf",
-        "check_estimator_sparse_tag": "KernelRidge does not support sparse data",
-        "check_estimator_sparse_array": "KernelRidge does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "KernelRidge does not handle sparse matrices gracefully",
         "check_regressors_train": "KernelRidge does not handle list inputs",
         "check_regressors_train(readonly_memmap=True)": "KernelRidge does not handle readonly memmap",
         "check_regressors_train(readonly_memmap=True,X_dtype=float32)": "KernelRidge does not handle readonly memmap with float32",
@@ -122,9 +116,6 @@
         "check_dtype_object": "LinearRegression does not handle object dtype",
         "check_estimators_empty_data_messages": "LinearRegression does not handle empty data",
         "check_estimators_nan_inf": "LinearRegression does not check for NaN and inf",
-        "check_estimator_sparse_tag": "LinearRegression does not support sparse data",
-        "check_estimator_sparse_array": "LinearRegression does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "LinearRegression does not handle sparse matrices gracefully",
         "check_regressors_train": "LinearRegression does not handle list inputs",
         "check_regressors_train(readonly_memmap=True)": "LinearRegression does not handle readonly memmap",
         "check_regressors_train(readonly_memmap=True,X_dtype=float32)": "LinearRegression does not handle readonly memmap with float32",
@@ -145,9 +136,6 @@
         "check_complex_data": "Ridge does not handle complex data",
         "check_dtype_object": "Ridge does not handle object dtype",
         "check_estimators_nan_inf": "Ridge does not check for NaN and inf",
-        "check_estimator_sparse_tag": "Ridge does not support sparse data",
-        "check_estimator_sparse_array": "Ridge does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "Ridge does not handle sparse matrices gracefully",
         "check_regressors_train": "Ridge does not handle list inputs",
         "check_regressors_train(readonly_memmap=True)": "Ridge does not handle readonly memmap",
         "check_regressors_train(readonly_memmap=True,X_dtype=float32)": "Ridge does not handle readonly memmap with float32",
@@ -167,9 +155,6 @@
         "check_dtype_object": "RandomForestRegressor does not handle object dtype",
         "check_estimators_empty_data_messages": "RandomForestRegressor does not handle empty data",
         "check_estimators_nan_inf": "RandomForestRegressor does not check for NaN and inf",
-        "check_estimator_sparse_tag": "RandomForestRegressor does not support sparse data",
-        "check_estimator_sparse_array": "RandomForestRegressor does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "RandomForestRegressor does not handle sparse matrices gracefully",
         "check_regressors_train": "RandomForestRegressor does not handle list inputs",
         "check_regressors_train(readonly_memmap=True)": "RandomForestRegressor does not handle readonly memmap",
         "check_regressors_train(readonly_memmap=True,X_dtype=float32)": "RandomForestRegressor does not handle readonly memmap with float32",
@@ -208,9 +193,6 @@
         "check_dtype_object": "RandomForestClassifier does not handle object dtype",
         "check_estimators_empty_data_messages": "RandomForestClassifier does not handle empty data",
         "check_estimators_nan_inf": "RandomForestClassifier does not check for NaN and inf",
-        "check_estimator_sparse_tag": "RandomForestClassifier does not support sparse data",
-        "check_estimator_sparse_array": "RandomForestClassifier does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "RandomForestClassifier does not handle sparse matrices gracefully",
         "check_classifier_data_not_an_array": "RandomForestClassifier does not handle non-array data",
         "check_classifiers_train": "RandomForestClassifier does not handle list inputs",
         "check_classifiers_train(readonly_memmap=True)": "RandomForestClassifier does not handle readonly memmap",
@@ -263,9 +245,6 @@
         "check_complex_data": "LinearSVC does not handle complex data",
         "check_dtype_object": "LinearSVC does not handle object dtype",
         "check_estimators_nan_inf": "LinearSVC does not check for NaN and inf",
-        "check_estimator_sparse_tag": "LinearSVC does not support sparse data",
-        "check_estimator_sparse_array": "LinearSVC does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "LinearSVC does not handle sparse matrices gracefully",
         "check_estimators_pickle": "LinearSVC does not support pickling",
         "check_estimators_pickle(readonly_memmap=True)": "LinearSVC does not support pickling with readonly memmap",
         "check_classifier_data_not_an_array": "LinearSVC does not handle non-array data",
@@ -293,9 +272,6 @@
         "check_complex_data": "LinearSVR does not handle complex data",
         "check_dtype_object": "LinearSVR does not handle object dtype",
         "check_estimators_nan_inf": "LinearSVR does not check for NaN and inf",
-        "check_estimator_sparse_tag": "LinearSVR does not support sparse data",
-        "check_estimator_sparse_array": "LinearSVR does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "LinearSVR does not handle sparse matrices gracefully",
         "check_regressors_train": "LinearSVR does not handle list inputs",
         "check_regressors_train(readonly_memmap=True)": "LinearSVR does not handle readonly memmap",
         "check_regressors_train(readonly_memmap=True,X_dtype=float32)": "LinearSVR does not handle readonly memmap with float32",
@@ -387,9 +363,6 @@
         "check_dtype_object": "TruncatedSVD does not handle object dtype",
         "check_estimators_empty_data_messages": "TruncatedSVD does not handle empty data",
         "check_estimators_nan_inf": "TruncatedSVD does not check for NaN and inf",
-        "check_estimator_sparse_tag": "TruncatedSVD does not support sparse data",
-        "check_estimator_sparse_array": "TruncatedSVD does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "TruncatedSVD does not handle sparse matrices gracefully",
         "check_transformer_data_not_an_array": "TruncatedSVD does not handle non-array data",
         "check_fit2d_1sample": "TruncatedSVD does not handle single sample",
         "check_fit2d_1feature": "TruncatedSVD does not handle single feature",
@@ -429,9 +402,6 @@
         "check_complex_data": "Lasso does not handle complex data",
         "check_dtype_object": "Lasso does not handle object dtype",
         "check_estimators_nan_inf": "Lasso does not check for NaN and inf",
-        "check_estimator_sparse_tag": "Lasso does not support sparse data",
-        "check_estimator_sparse_array": "Lasso does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "Lasso does not handle sparse matrices gracefully",
         "check_regressors_train": "Lasso does not handle list inputs",
         "check_regressors_train(readonly_memmap=True)": "Lasso does not handle readonly memmap",
         "check_regressors_train(readonly_memmap=True,X_dtype=float32)": "Lasso does not handle readonly memmap with float32",
@@ -452,9 +422,6 @@
         "check_complex_data": "ElasticNet does not handle complex data",
         "check_dtype_object": "ElasticNet does not handle object dtype",
         "check_estimators_nan_inf": "ElasticNet does not check for NaN and inf",
-        "check_estimator_sparse_tag": "ElasticNet does not support sparse data",
-        "check_estimator_sparse_array": "ElasticNet does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "ElasticNet does not handle sparse matrices gracefully",
         "check_regressors_train": "ElasticNet does not handle list inputs",
         "check_regressors_train(readonly_memmap=True)": "ElasticNet does not handle readonly memmap",
         "check_regressors_train(readonly_memmap=True,X_dtype=float32)": "ElasticNet does not handle readonly memmap with float32",
@@ -474,9 +441,6 @@
         "check_complex_data": "KernelDensity does not handle complex data",
         "check_dtype_object": "KernelDensity does not handle object dtype",
         "check_estimators_nan_inf": "KernelDensity does not check for NaN and inf",
-        "check_estimator_sparse_tag": "KernelDensity does not support sparse data",
-        "check_estimator_sparse_array": "KernelDensity does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "KernelDensity does not handle sparse matrices gracefully",
         "check_fit1d": "KernelDensity does not raise ValueError for 1D input",
     },
     LedoitWolf: {
@@ -486,9 +450,6 @@
         "check_dtype_object": "LedoitWolf does not handle object dtype",
         "check_estimators_empty_data_messages": "LedoitWolf does not handle empty data",
         "check_estimators_nan_inf": "LedoitWolf does not check for NaN and inf",
-        "check_estimator_sparse_tag": "LedoitWolf does not support sparse data",
-        "check_estimator_sparse_array": "LedoitWolf does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "LedoitWolf does not handle sparse matrices gracefully",
     },
     DBSCAN: {
         "check_estimator_tags_renamed": "No support for modern tags infrastructure",
@@ -499,9 +460,6 @@
         "check_dtype_object": "DBSCAN does not handle object dtype",
         "check_estimators_empty_data_messages": "DBSCAN does not handle empty data",
         "check_estimators_nan_inf": "DBSCAN does not check for NaN and inf",
-        "check_estimator_sparse_tag": "DBSCAN does not support sparse data",
-        "check_estimator_sparse_array": "DBSCAN does not handle sparse arrays gracefully",
-        "check_estimator_sparse_matrix": "DBSCAN does not handle sparse matrices gracefully",
         "check_fit1d": "DBSCAN does not raise ValueError for 1D input",
     },
     HDBSCAN: {
@@ -512,7 +470,6 @@
         "check_dtype_object": "HDBSCAN does not handle object dtype",
         "check_estimators_empty_data_messages": "HDBSCAN does not handle empty data",
         "check_estimators_nan_inf": "HDBSCAN does not check for NaN and inf",
-        "check_estimator_sparse_tag": "HDBSCAN does not support sparse data",
         "check_estimator_sparse_array": "HDBSCAN does not handle sparse arrays gracefully",
         "check_estimator_sparse_matrix": "HDBSCAN does not handle sparse matrices gracefully",
         "check_parameters_default_constructible": "HDBSCAN parameters are mutated on init",
@@ -537,7 +494,6 @@
         "check_complex_data": "AgglomerativeClustering does not handle complex data",
         "check_dtype_object": "AgglomerativeClustering does not handle object dtype",
         "check_estimators_nan_inf": "AgglomerativeClustering does not check for NaN and inf",
-        "check_estimator_sparse_tag": "AgglomerativeClustering does not support sparse data",
         "check_estimator_sparse_array": "AgglomerativeClustering does not handle sparse arrays gracefully",
         "check_estimator_sparse_matrix": "AgglomerativeClustering does not handle sparse matrices gracefully",
         "check_parameters_default_constructible": "AgglomerativeClustering parameters are mutated on init",
@@ -556,8 +512,6 @@
         "check_dtype_object": "GaussianNB does not handle object dtype",
         "check_estimators_empty_data_messages": "GaussianNB does not handle empty data",
         "check_estimators_nan_inf": "GaussianNB does not check for NaN and inf",
-        "check_estimator_sparse_tag": "GaussianNB does not support sparse data",
-        "check_estimator_sparse_array": "GaussianNB does not handle sparse arrays gracefully",
         "check_classifier_data_not_an_array": "GaussianNB does not handle non-array data",
         "check_classifiers_classes": "GaussianNB does not handle string data properly",
         "check_estimators_partial_fit_n_features": "GaussianNB does not check n_features consistency in partial_fit",
@@ -586,7 +540,7 @@
         "check_estimators_empty_data_messages": "GaussianRandomProjection does not handle empty data",
         "check_pipeline_consistency": "GaussianRandomProjection raises ValueError with small datasets",
         "check_estimators_nan_inf": "GaussianRandomProjection does not check for NaN and inf",
-        "check_estimator_sparse_tag": "GaussianRandomProjection does not support sparse data",
+        "check_estimator_sparse_tag": "GaussianRandomProjection raises ValueError with small datasets even though it supports sparse inputs",
         "check_estimator_sparse_array": "GaussianRandomProjection does not handle sparse arrays gracefully",
         "check_estimator_sparse_matrix": "GaussianRandomProjection does not handle sparse matrices gracefully",
         "check_estimators_pickle": "GaussianRandomProjection raises ValueError with small datasets",
@@ -615,7 +569,7 @@
         "check_estimators_empty_data_messages": "SparseRandomProjection does not handle empty data",
         "check_pipeline_consistency": "SparseRandomProjection raises ValueError with small datasets",
         "check_estimators_nan_inf": "SparseRandomProjection does not check for NaN and inf",
-        "check_estimator_sparse_tag": "SparseRandomProjection does not support sparse data",
+        "check_estimator_sparse_tag": "SparseRandomProjection raises ValueError with small datasets",
         "check_estimator_sparse_array": "SparseRandomProjection does not handle sparse arrays gracefully",
         "check_estimator_sparse_matrix": "SparseRandomProjection does not handle sparse matrices gracefully",
         "check_estimators_pickle": "SparseRandomProjection raises ValueError with small datasets",
@@ -644,8 +598,6 @@
         "check_dtype_object": "BernoulliNB does not handle object dtype",
         "check_estimators_empty_data_messages": "BernoulliNB does not provide proper error messages for empty data",
         "check_estimators_nan_inf": "BernoulliNB does not check for NaN and inf",
-        "check_estimator_sparse_tag": "BernoulliNB sparse data handling does not follow sklearn conventions",
-        "check_estimator_sparse_array": "BernoulliNB does not handle sparse arrays gracefully",
         "check_classifier_data_not_an_array": "BernoulliNB does not handle list inputs",
         "check_classifiers_classes": "BernoulliNB does not handle string labels properly",
         "check_estimators_partial_fit_n_features": "BernoulliNB does not check n_features consistency in partial_fit",
@@ -677,8 +629,6 @@
         "check_estimators_empty_data_messages": "ComplementNB does not provide proper error messages for empty data",
         "check_pipeline_consistency": "ComplementNB pipeline consistency issues",
         "check_estimators_nan_inf": "ComplementNB does not check for NaN and inf",
-        "check_estimator_sparse_tag": "ComplementNB sparse data handling does not follow sklearn conventions",
-        "check_estimator_sparse_array": "ComplementNB does not handle sparse arrays gracefully",
         "check_estimators_pickle": "ComplementNB pickling issues",
         "check_estimators_pickle(readonly_memmap=True)": "ComplementNB pickling with readonly memmap issues",
         "check_classifier_data_not_an_array": "ComplementNB does not handle list inputs",
@@ -711,8 +661,6 @@
         "check_dtype_object": "CategoricalNB does not handle object dtype",
         "check_estimators_empty_data_messages": "CategoricalNB does not provide proper error messages for empty data",
         "check_estimators_nan_inf": "CategoricalNB does not check for NaN and inf",
-        "check_estimator_sparse_tag": "CategoricalNB sparse data handling does not follow sklearn conventions",
-        "check_estimator_sparse_array": "CategoricalNB does not handle sparse arrays gracefully",
         "check_classifier_data_not_an_array": "CategoricalNB does not handle list inputs",
         "check_classifiers_classes": "CategoricalNB does not handle string labels properly",
         "check_estimators_partial_fit_n_features": "CategoricalNB does not check n_features consistency in partial_fit",
@@ -739,8 +687,6 @@
         "check_dtype_object": "MultinomialNB does not handle object dtype",
         "check_estimators_empty_data_messages": "MultinomialNB does not provide proper error messages for empty data",
         "check_estimators_nan_inf": "MultinomialNB does not check for NaN and inf",
-        "check_estimator_sparse_tag": "MultinomialNB sparse data handling does not follow sklearn conventions",
-        "check_estimator_sparse_array": "MultinomialNB does not handle sparse arrays gracefully",
         "check_classifier_data_not_an_array": "MultinomialNB does not handle non-array data",
         "check_classifiers_classes": "MultinomialNB does not handle string labels properly",
         "check_estimators_partial_fit_n_features": "MultinomialNB does not check n_features consistency in partial_fit",