diff --git a/src/unitxt/metrics.py b/src/unitxt/metrics.py
index 9942c1be6d..5e4930b255 100644
--- a/src/unitxt/metrics.py
+++ b/src/unitxt/metrics.py
@@ -4408,6 +4408,8 @@ def compute(
             self._compute_single_ref(str(reference), str(prediction))
             for reference in references
         ]
+        if not results:
+            return {"precision": 0, "recall": 0, "f1": 0}
         return {
             measure: max(r[i] for r in results)
             for i, measure in enumerate(["precision", "recall", "f1"])
diff --git a/tests/library/test_metrics.py b/tests/library/test_metrics.py
index 097856d267..d051273456 100644
--- a/tests/library/test_metrics.py
+++ b/tests/library/test_metrics.py
@@ -1190,6 +1190,17 @@ def test_token_overlap(self):
         for target, value in global_targets.items():
             self.assertAlmostEqual(value, outputs[0]["score"]["global"][target])
 
+    def test_token_overlap_empty_references(self):
+        metric = TokenOverlap()
+        predictions = ["hello there"]
+        references = [[]]
+        outputs = apply_metric(
+            metric=metric, predictions=predictions, references=references
+        )
+        global_targets = {"f1": 0, "precision": 0, "recall": 0}
+        for target, value in global_targets.items():
+            self.assertAlmostEqual(value, outputs[0]["score"]["global"][target])
+
     def test_roc_auc(self):
         metric = RocAuc()
         predictions = [0.2, 0.8, 1.0]