diff --git a/tests/onnxruntime/test_modeling.py b/tests/onnxruntime/test_modeling.py
index a249690838..e8484b34f8 100644
--- a/tests/onnxruntime/test_modeling.py
+++ b/tests/onnxruntime/test_modeling.py
@@ -1250,7 +1250,7 @@ class ORTModelForQuestionAnsweringIntegrationTest(ORTModelTestMixin):
         "roberta",
         "roformer",
         "squeezebert",
-        "xlm",
+        "xlm_qa",
         "xlm_roberta",
     ]
 
diff --git a/tests/onnxruntime/utils_onnxruntime_tests.py b/tests/onnxruntime/utils_onnxruntime_tests.py
index b262814576..ddec82f23f 100644
--- a/tests/onnxruntime/utils_onnxruntime_tests.py
+++ b/tests/onnxruntime/utils_onnxruntime_tests.py
@@ -149,6 +149,7 @@
     "wav2vec2-conformer": "hf-internal-testing/tiny-random-wav2vec2-conformer",
     "wavlm": "hf-internal-testing/tiny-random-WavlmModel",
     "xlm": "hf-internal-testing/tiny-random-XLMModel",
+    "xlm_qa": "hf-internal-testing/tiny-random-XLMForQuestionAnsweringSimple",  # issue with default hf-internal-testing in transformers QA pipeline post-processing
     "xlm_roberta": "hf-internal-testing/tiny-xlm-roberta",
     "yolos": "hf-internal-testing/tiny-random-YolosModel",
 }