Correctness Judge

The Correctness judge assesses whether your GenAI application's response is factually correct by comparing it against provided ground truth information (expected_facts or expected_response).

This built-in LLM judge is designed for evaluating application responses against known correct answers.

Prerequisites for running the examples

1. Install MLflow and required packages

   bash

   pip install --upgrade mlflow

2. Create an MLflow experiment by following the setup your environment quickstart.

3. (Optional, if using OpenAI models) Use the native OpenAI SDK to connect to OpenAI-hosted models. Select a model from the available OpenAI models.

   python

   import mlflow
   import os
   import openai
   
   # Ensure your OPENAI_API_KEY is set in your environment
   # os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>" # Uncomment and set if not globally configured
   
   # Enable auto-tracing for OpenAI
   mlflow.openai.autolog()
   
   # Create an OpenAI client
   client = openai.OpenAI()
   
   # Select an LLM
   model_name = "gpt-4o-mini"

Usage examples

Invoke directly

python

from mlflow.genai.scorers import Correctness

correctness_judge = Correctness()

# Example 1: Response contains expected facts
feedback = correctness_judge(
    inputs={"request": "What is MLflow?"},
    outputs={
        "response": "MLflow is an open-source platform for managing the ML lifecycle."
    },
    expectations={
        "expected_facts": [
            "MLflow is open-source",
            "MLflow is a platform for ML lifecycle",
        ]
    },
)

# Example 2: Response missing or contradicting facts
feedback = correctness_judge(
    inputs={"request": "When was MLflow released?"},
    outputs={"response": "MLflow was released in 2017."},
    expectations={"expected_facts": ["MLflow was released in June 2018"]},
)

# Example 3: Using expected_response instead of expected_facts
feedback = correctness_judge(
    inputs={"request": "What is the capital of France?"},
    outputs={"response": "The capital of France is Paris."},
    expectations={"expected_response": "Paris is the capital of France."},
)

Invoke with evaluate()

python

import mlflow
from mlflow.genai.scorers import Correctness

# Create evaluation dataset with ground truth
eval_dataset = [
    # Example 1: Response contains expected facts
    {
        "inputs": {"request": "What is MLflow?"},
        "outputs": {
            "response": "MLflow is an open-source platform for managing the ML lifecycle."
        },
        "expectations": {
            "expected_facts": [
                "MLflow is open-source",
                "MLflow is a platform for ML lifecycle",
            ]
        },
    },
    # Example 2: Response missing or contradicting facts
    {
        "inputs": {"request": "When was MLflow released?"},
        "outputs": {"response": "MLflow was released in 2017."},
        "expectations": {"expected_facts": ["MLflow was released in June 2018"]},
    },
    # Example 3: Using expected_response instead of expected_facts
    {
        "inputs": {"request": "What is the capital of France?"},
        "outputs": {"response": "The capital of France is Paris."},
        "expectations": {"expected_response": "Paris is the capital of France."},
    },
]

# Run evaluation with Correctness judge
eval_results = mlflow.genai.evaluate(
    data=eval_dataset,
    scorers=[
        Correctness(
            model="openai:/gpt-4o-mini",  # Optional.
        )
    ],
)

tip

Use expected_facts rather than expected_response for more flexible evaluation - the response doesn't need to match word-for-word, just contain the key facts.

Select the LLM that powers the judge

You can change the judge model by using the model argument in the judge definition. The model must be specified in the format <provider>:/<model-name>, where <provider> is a LiteLLM-compatible model provider.

For a list of supported models, see selecting judge models.

Interpret results

The judge returns a Feedback object with:

• value: "yes" if response is correct, "no" if incorrect
• rationale: Detailed explanation of which facts are supported or missing

Next steps

Explore other built-in judges

Learn about other built-in quality evaluation judges

Learn more →

Create custom judges

Build domain-specific evaluation judges

Learn more →

Build evaluation datasets

Create test cases with ground truth for testing

Learn more →