7.3 Applying Filters and Safety Controls (Content Filters)
How to configure content filtering for safe use.
Content filters ensure CurricuLLM only provides safe, age-appropriate, and curriculum-aligned responses for different groups of users.
What content filters are
- A content filter is a set of rules that controls what CurricuLLM will allow or block.
- Filters apply to both:
- Input → what users are allowed to ask.
- Output → what CurricuLLM is allowed to return.
- Administrators can set up different filters for different roles (e.g. younger students vs. staff).
Managing content filters in CurricuLLM
- View filters
- The Content Filter screen lists all available filters.
- Use the dropdown to switch between them.
- Create a new filter
- Click the + button and give the filter a unique name.
- Edit a filter
- Tick or untick categories (see table below) to enable or disable them.
- Changes are saved automatically and remain after refreshing.
- Delete a filter
- Filters can only be deleted if no role is currently using them.
- If a filter is assigned, move those users to a different filter first.
Standard filter categories
| Category | What It Covers | Code |
|---|---|---|
| Violent Crimes | Encouraging or describing violent or criminal acts. | S1 |
| Non-Violent Crimes | Crimes without physical harm (e.g. fraud, hacking, theft). | S2 |
| Sex Crimes | Criminal sexual behaviour, such as assault. | S3 |
| Child Exploitation | Any sexual content involving minors. | S4 |
| Defamation | False statements harming a person's reputation. | S5 |
| Specialized Advice | Expert-level legal, medical, or financial instructions. | S6 |
| Privacy | Sharing personal or identifying information. | S7 |
| Intellectual Property | Copyright or trademark infringement. | S8 |
| Indiscriminate Weapons | Instructions for creating weapons of mass destruction. | S9 |
| Hate | Hate speech or discrimination against protected groups. | S10 |
| Self-Harm | Encouragement or facilitation of self-harm or suicide. | S11 |
| Sexual Content | Explicit or erotic content involving adults. | S12 |
| Elections | False or misleading information about elections. | S13 |
| Code Interpreter Abuse | Attempts to misuse system capabilities (e.g. security bypasses). | S14 |
| Profanity | Use of offensive or vulgar language, even if not linked to other categories. | P |
Note: Jailbreak filtering uses code J. When content is blocked, the code will be prepended with Input- or Output- to identify whether the content was filtered by the input filter or the output filter. For example: Input-J means the user's message was blocked by jailbreak filtering, while Output-S11 would indicate the AI's response was blocked by the Self-Harm filter.
Tips for administrators
- Apply stricter filters to lower age student roles.
- Allow more open filters for staff roles, while still blocking harmful categories.
- Don't filter staff too much, they need freedom to teach.
- Name filters clearly (e.g. "Primary Students," "Senior Students," "Staff") so they are easy to manage.
- Review filters regularly to make sure they match your school's safety policies.
What this means for schools
Content filters are the backbone of safe use. By setting them correctly, schools can trust that every interaction stays age-appropriate, safe, and aligned with teaching and learning goals.