diff --git a/docs/Changelog-ml.md b/docs/Changelog-ml.md
index 1a84d5c0460..0beb74a5022 100644
--- a/docs/Changelog-ml.md
+++ b/docs/Changelog-ml.md
@@ -1085,9 +1085,9 @@ This version of the operator has been available since version 3 of the 'ai.onnx.
 <dt><tt>aggregate_function</tt> : string (default is SUM)</dt>
 <dd>Defines how to aggregate leaf values within a target. <br>One of 'AVERAGE,' 'SUM,' 'MIN,' 'MAX.'</dd>
 <dt><tt>base_values</tt> : list of floats</dt>
-<dd>Base values for classification, added to final class score; the size must be the same as the classes or can be left unassigned (assumed 0)</dd>
+<dd>Base values for regression, added to final prediction after applying aggregate_function; the size must be the same as the classes or can be left unassigned (assumed 0)</dd>
 <dt><tt>base_values_as_tensor</tt> : tensor</dt>
-<dd>Base values for classification, added to final class score; the size must be the same as the classes or can be left unassigned (assumed 0)</dd>
+<dd>Base values for regression, added to final prediction after applying aggregate_function; the size must be the same as the classes or can be left unassigned (assumed 0)</dd>
 <dt><tt>n_targets</tt> : int</dt>
 <dd>The total number of targets.</dd>
 <dt><tt>nodes_falsenodeids</tt> : list of ints</dt>
diff --git a/docs/Operators-ml.md b/docs/Operators-ml.md
index 17f360d5b56..decdb54b316 100644
--- a/docs/Operators-ml.md
+++ b/docs/Operators-ml.md
@@ -1038,9 +1038,9 @@ Other versions of this operator: <a href="Changelog-ml.md#ai.onnx.ml.TreeEnsembl
 <dt><tt>aggregate_function</tt> : string (default is SUM)</dt>
 <dd>Defines how to aggregate leaf values within a target. <br>One of 'AVERAGE,' 'SUM,' 'MIN,' 'MAX.'</dd>
 <dt><tt>base_values</tt> : list of floats</dt>
-<dd>Base values for classification, added to final class score; the size must be the same as the classes or can be left unassigned (assumed 0)</dd>
+<dd>Base values for regression, added to final prediction after applying aggregate_function; the size must be the same as the classes or can be left unassigned (assumed 0)</dd>
 <dt><tt>base_values_as_tensor</tt> : tensor</dt>
-<dd>Base values for classification, added to final class score; the size must be the same as the classes or can be left unassigned (assumed 0)</dd>
+<dd>Base values for regression, added to final prediction after applying aggregate_function; the size must be the same as the classes or can be left unassigned (assumed 0)</dd>
 <dt><tt>n_targets</tt> : int</dt>
 <dd>The total number of targets.</dd>
 <dt><tt>nodes_falsenodeids</tt> : list of ints</dt>
diff --git a/onnx/defs/traditionalml/defs.cc b/onnx/defs/traditionalml/defs.cc
index 50e1c5d3f0b..7a1e98ceb0d 100644
--- a/onnx/defs/traditionalml/defs.cc
+++ b/onnx/defs/traditionalml/defs.cc
@@ -998,12 +998,12 @@ ONNX_ML_OPERATOR_SET_SCHEMA(
             std::string("SUM"))
         .Attr(
             "base_values",
-            "Base values for classification, added to final class score; the size must be the same as the classes or can be left unassigned (assumed 0)",
+            "Base values for regression, added to final prediction after applying aggregate_function; the size must be the same as the classes or can be left unassigned (assumed 0)",
             AttributeProto::FLOATS,
             OPTIONAL_VALUE)
         .Attr(
             "base_values_as_tensor",
-            "Base values for classification, added to final class score; the size must be the same as the classes or can be left unassigned (assumed 0)",
+            "Base values for regression, added to final prediction after applying aggregate_function; the size must be the same as the classes or can be left unassigned (assumed 0)",
             AttributeProto::TENSOR,
             OPTIONAL_VALUE)
         .TypeAndShapeInferenceFunction([](InferenceContext& ctx) {
diff --git a/onnx/reference/ops/aionnxml/op_tree_ensemble_regressor.py b/onnx/reference/ops/aionnxml/op_tree_ensemble_regressor.py
index 453980bd0fe..a9916279d94 100644
--- a/onnx/reference/ops/aionnxml/op_tree_ensemble_regressor.py
+++ b/onnx/reference/ops/aionnxml/op_tree_ensemble_regressor.py
@@ -97,8 +97,10 @@ def _run(  # type: ignore
                 )
         if aggregate_function == "AVERAGE":
             res /= n_trees
+
+        # Convention is to add base_values after aggregate function
         if base_values is not None:
-            res[:, :] = np.array(base_values).reshape((1, -1))
+            res[:, :] += np.array(base_values).reshape((1, -1))
 
         if post_transform in (None, "NONE"):
             return (res,)
diff --git a/onnx/test/reference_evaluator_ml_test.py b/onnx/test/reference_evaluator_ml_test.py
index 71a9175601e..8f67654ef43 100644
--- a/onnx/test/reference_evaluator_ml_test.py
+++ b/onnx/test/reference_evaluator_ml_test.py
@@ -10,6 +10,7 @@
 
 import numpy as np  # type: ignore
 from numpy.testing import assert_allclose  # type: ignore
+from parameterized import parameterized
 
 from onnx import ONNX_ML, TensorProto, TypeProto, ValueInfoProto
 from onnx.checker import check_model
@@ -757,7 +758,7 @@ def test_linear_classifier_unary(self):
 
     @staticmethod
     def _get_test_tree_ensemble_regressor(
-        aggregate_function, rule="BRANCH_LEQ", unique_targets=False
+        aggregate_function, rule="BRANCH_LEQ", unique_targets=False, base_values=None
     ):
         X = make_tensor_value_info("X", TensorProto.FLOAT, [None, None])
         Y = make_tensor_value_info("Y", TensorProto.FLOAT, [None, None])
@@ -786,6 +787,7 @@ def _get_test_tree_ensemble_regressor(
             domain="ai.onnx.ml",
             n_targets=1,
             aggregate_function=aggregate_function,
+            base_values=base_values,
             nodes_falsenodeids=[4, 3, 0, 0, 0, 2, 0, 4, 0, 0],
             nodes_featureids=[0, 2, 0, 0, 0, 0, 0, 2, 0, 0],
             nodes_hitrates=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0],
@@ -828,8 +830,17 @@ def _get_test_tree_ensemble_regressor(
         check_model(onx)
         return onx
 
+    @parameterized.expand(
+        [
+            (f"{agg}_{base_values}", base_values, agg)
+            for base_values in (None, [1.0])
+            for agg in ("SUM", "AVERAGE", "MIN", "MAX")
+        ]
+    )
     @unittest.skipIf(not ONNX_ML, reason="onnx not compiled with ai.onnx.ml")
-    def test_tree_ensemble_regressor(self):
+    def test_tree_ensemble_regressor(self, name, base_values, agg):
+        self.assertTrue(ONNX_ML)
+        del name  # variable only used to print test name
         x = np.arange(9).reshape((-1, 3)).astype(np.float32) / 10 - 0.5
         expected_agg = {
             "SUM": np.array([[0.576923], [0.576923], [0.576923]], dtype=np.float32),
@@ -837,14 +848,16 @@ def test_tree_ensemble_regressor(self):
             "MIN": np.array([[0.076923], [0.076923], [0.076923]], dtype=np.float32),
             "MAX": np.array([[0.5], [0.5], [0.5]], dtype=np.float32),
         }
-        for agg in ("SUM", "AVERAGE", "MIN", "MAX"):
-            expected = expected_agg[agg]
-            with self.subTest(aggregate_function=agg):
-                onx = self._get_test_tree_ensemble_regressor(agg)
-                self._check_ort(onx, {"X": x}, equal=True)
-                sess = ReferenceEvaluator(onx)
-                got = sess.run(None, {"X": x})
-                assert_allclose(expected, got[0], atol=1e-6)
+
+        expected = expected_agg[agg]
+        if base_values is not None:
+            expected += base_values[0]
+        with self.subTest(aggregate_function=agg):
+            onx = self._get_test_tree_ensemble_regressor(agg, base_values=base_values)
+            self._check_ort(onx, {"X": x}, equal=True)
+            sess = ReferenceEvaluator(onx)
+            got = sess.run(None, {"X": x})
+            assert_allclose(expected, got[0], atol=1e-6)
 
     @unittest.skipIf(not ONNX_ML, reason="onnx not compiled with ai.onnx.ml")
     def test_tree_ensemble_regressor_rule(self):