FaithfulnessScorer
Measures how faithful the generated answer is to the provided context. Critical RAG metric that evaluates whether the answer is grounded in and supported by retrieved documents, detecting hallucinations and unsupported claims.
Overview
Measures how faithful the generated answer is to the provided context. Critical RAG metric that evaluates whether the answer is grounded in and supported by retrieved documents, detecting hallucinations and unsupported claims.
Use Cases
- RAG-based question answering systems
- Safety and compliance monitoring
- Hallucination detection in generated content
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 | The generated answer to verify |
| input_text | str | No | The original question |
| context | dict | str | list | Yes | Retrieved context/documents |
Output Schema
| Field | Type | Description |
|---|---|---|
| score | float | Faithfulness score (0-10) |
| passed | bool | True if faithful to context |
| reasoning | str | Claim verification details |
| metadata.claims | list | Extracted claims and verification status |
Score Interpretation
Default threshold: 7/10
Related Scorers
FactualAccuracyScorer
Evaluates factual accuracy of output text against provided context. Assesses whether statements in t...
HallucinationHallucinationDetectionScorer
Detects hallucinations and factual inconsistencies in generated answers by comparing against source ...
Multi-ContextContextGroundednessScorer
Evaluates how well an answer is grounded in and supported by the provided context. Ensures claims ca...
RAGAnswerRelevancyScorer
Evaluates how relevant the generated answer is to the input question. Assesses whether the response ...
Frequently Asked Questions
When should I use this scorer?
Use FaithfulnessScorer when you need to evaluate rag and hallucination aspects of your AI outputs. It's particularly useful for rag-based question answering systems.
Why doesn't this scorer need expected output?
This scorer evaluates without a reference answer by using the specific input fields listed in its schema. Those fields are evidence for the check; they are not automatically factual ground truth.
Can I customize the threshold?
This scorer's displayed default threshold is 7. Where the eval-job configuration exposes a threshold, review it against the scorer's native scale before saving. The stored pass decision uses that scorer-specific configuration.
Quick Info
Ready to try FaithfulnessScorer?
Start evaluating your AI agents with Noveum.ai's comprehensive scorer library.
Explore More Scorers
Discover 112 published scorers across 15 categories: 82 Premium, 30 Free, 76 model-backed, and 36 dedicated voice and audio scorers