Skip to main content

Instructors - Understanding Chat Moderation

Updated this week

For all conversation activities learners engage with within a lesson, our AI will moderate based on the content of your responses. The following categories will typically trigger our AI moderation:

Category

Description

harassment

Content that expresses, incites, or promotes harassing language towards any target.

harassment/threatening

Harassment content that also includes violence or serious harm towards any target.

hate

Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.

hate/threatening

Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.

illicit

Content that gives advice or instruction on how to commit illicit acts. A phrase like "how to shoplift" would fit this category.

illicit/violent

The same types of content flagged by the illicit category, but also includes references to violence or procuring a weapon.

self-harm

Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.

self-harm/intent

Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.

self-harm/instructions

Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.

sexual

Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).

sexual/minors

Sexual content that includes an individual who is under 18 years old.

violence

Content that depicts death, violence, or physical injury.

violence/graphic

Content that depicts death, violence, or physical injury in graphic detail.

You can have access to each asset’s transcripts to review your learners’ responses. Please reach out to your institution or Kyron Customer Success Manager to gain access to your Looker Dashboard.

When moderation is triggered, the learner will see the following message letting them know their response was flagged and prompting them to rephrase it.

“As a reminder, I’m an AI program. Your previous response included content that I’m not able to engage with. Please rephrase your last answer using different language and try again.”

If the revised response is flagged again, the learner will see another message, the conversation will end, and the activity will remain incomplete. Learners can reset the conversation and try again to complete the activity.

“I’m still seeing content that I cannot respond to, so I need to end this conversation. You can reset the conversation anytime to try again.”

Examples

Below are examples of responses that will trigger our moderation.

Question: Explain how oxygen and carbon dioxide are carried through the bloodstream and how their distinct binding locations on hemoglobin prevent competition between the two gases.

  • Moderated answer: With a punctured lung, when oxygen saturation falls, it seems like carbon dioxide is attaching to the same hemoglobin sites and blocking oxygen.

  • Revised answer: Puncture lung doesn’t let CO₂ block oxygen.

Question: Describe how calcium is regulated during the transition from contraction to relaxation and how this regulation allows the muscle fiber to return to its resting state.

  • Moderated answer: Following a crushing injury that risks localized tissue hemorrhage, the muscle may stay rigid, giving the impression that calcium removal is impaired.

  • Revised answer: Crushing trauma keeps calcium high.

Question: Describe how hormones regulate cartilage formation and bone replacement during bone repair.

  • Moderated answer: In a compound fracture with exposed tissue, it can look like cartilage directly ossifies into bone during the severe trauma response.

  • Revised answer: Compound fracture looks like cartilage hardens.

Did this answer your question?