Feedback Aide Evaluation Options

Evaluation options let you configure the models available in Feedback Aide.

Different models and different rubric types will accept different options and silently ignore options that not relevant to it.

In the JavaScript API, the evaluation options should be set when initializing a feedback session with the feedbackApp.feedbackSession() method.

When using the RESTful API, it can be passed via the options parameter on any of the evaluate endpoints.

The following evaluation options are available.

• annotations object

  Controls configuration options for text-highlighting based annotations on the learner's response.

• citation_check object

  Configuration options for checking if the essay response has the minimum required number of citations.

• grading object

  Provide additional context to the model about the learner level and the marking style required for this evaluation.

• justification_of_score object

  Configuration options for enabling the model to return an explanation of the score.

• language string

  Controls the language of the generated feedback.

• language_check object

  Checks if the essay response is written in the expected language.

• moderation object

  Configuration options for moderating sensitive, inappropriate, or crisis-related content in responses.

• structure_check object

  Configuration options for checking if the essay matches the required paragraph structure.

• topic_check object

  Checks if the essay is on a topic related to the question.