diff --git a/docs/reference/ingest/processors/inference.asciidoc b/docs/reference/ingest/processors/inference.asciidoc
index 89e8a2ae13cc0..0995e3f643813 100644
--- a/docs/reference/ingest/processors/inference.asciidoc
+++ b/docs/reference/ingest/processors/inference.asciidoc
@@ -30,7 +30,7 @@ include::common-options.asciidoc[]
 * You cannot use the `input_output` field with the `target_field` and 
 `field_map` fields. For NLP models, use the `input_output` option. For 
 {dfanalytics} models, use the `target_field` and `field_map` option.
-* The {infer} input fields must be single strings, not arrays of strings.
+* Each {infer} input field must be single strings, not arrays of strings.
 ==================================================
 
 [discrete]
diff --git a/docs/reference/ml/trained-models/apis/infer-trained-model.asciidoc b/docs/reference/ml/trained-models/apis/infer-trained-model.asciidoc
index 3cf3ac07708c5..d7201fcf42c0a 100644
--- a/docs/reference/ml/trained-models/apis/infer-trained-model.asciidoc
+++ b/docs/reference/ml/trained-models/apis/infer-trained-model.asciidoc
@@ -57,8 +57,8 @@ Controls the amount of time to wait for {infer} results. Defaults to 10 seconds.
 (Required, array)
 An array of objects to pass to the model for inference. The objects should
 contain the fields matching your configured trained model input. Typically for
-NLP models, the field name is `text_field`. The {infer} input fields must be 
-single strings not arrays of strings.
+NLP models, the field name is `text_field`. Each {infer} input field specified 
+in this property must be single strings not arrays of strings.
 
 //Begin inference_config
 `inference_config`::