ContentModerationScorer
Evaluates content against moderation guidelines and policies. Checks for violations across multiple categories including violence, hate speech, adult content, and self-harm. Essential for platform safety.
Overview
Evaluates content against moderation guidelines and policies. Checks for violations across multiple categories including violence, hate speech, adult content, and self-harm. Essential for platform safety.
Use Cases
- Safety and compliance monitoring
How It Works
This scorer uses LLM-as-Judge technology to evaluate responses. It prompts a large language model with specific evaluation criteria and the content to assess, then analyzes the LLM's judgment to produce a score and detailed reasoning.
Input Schema
| Parameter | Type | Required | Description |
|---|---|---|---|
| output_text | str | Yes | Content to moderate |
| input_text | str | No | Original input prompt |
| context.guidelines | str | No | Moderation guidelines |
Output Schema
| Field | Type | Description |
|---|---|---|
| score | float | Content safety score (0-10, 10=safe) |
| passed | bool | True if content passes moderation |
| reasoning | str | Moderation analysis |
| metadata.violations | list | Specific policy violations |
Score Interpretation
Default threshold: 7/10
Related Scorers
ContentSafetyViolationScorer
Detects specific safety policy violations in generated content. More granular than general moderatio...
SafetyToxicityScorer
Measures the level of toxic content in generated text. Evaluates text for various forms of toxicity ...
SafetyIsHarmfulAdviceScorer
Evaluates whether generated content contains harmful advice or dangerous recommendations. Detects ad...
SafetyAnswerRefusalScorer
Evaluates whether the model appropriately refuses to answer harmful or inappropriate requests. Asses...
Frequently Asked Questions
When should I use this scorer?
Use ContentModerationScorer when you need to evaluate safety and llm-judge aspects of your AI outputs. It's particularly useful for safety and compliance monitoring.
Why doesn't this scorer need expected output?
This scorer evaluates quality aspects that don't require comparison against a reference answer. It uses the system prompt and context as the implicit ground truth.
Can I customize the threshold?
Yes, the default threshold of 7 can be customized when configuring the scorer.
Quick Info
Ready to try ContentModerationScorer?
Start evaluating your AI agents with Noveum.ai's comprehensive scorer library.
Explore More Scorers
Discover 106 calibrated LLM-as-Judge scorers for comprehensive AI evaluation