> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Response Quality Metrics

> Evaluate how correctly, consistently, and in line with ground truth your AI follows instructions and answers user queries

export const ModalityIcons = ({modalities}) => {
  const iconProps = {
    fill: "none",
    height: 20,
    width: 20,
    stroke: "currentColor",
    strokeLinecap: "round",
    strokeLinejoin: "round",
    strokeWidth: 2,
    viewBox: "0 0 24 24",
    xmlns: "http://www.w3.org/2000/svg"
  };
  const renderIcon = modality => {
    if (modality === "Text") {
      return <svg {...iconProps} aria-hidden="true">
          <circle cx="12" cy="12" r="9" />
          <path d="M8 8h8M12 8v8" />
        </svg>;
    }
    if (modality === "Image/PDF") {
      return <svg {...iconProps} aria-hidden="true">
          <rect height="18" rx="2" width="18" x="3" y="3" />
          <circle cx="8.5" cy="8.5" r="1.5" />
          <path d="m21 15-5-5L5 21" />
        </svg>;
    }
    if (modality === "Audio") {
      return <svg {...iconProps} aria-hidden="true">
          <path d="M9 18V5l10-2v13" />
          <circle cx="6" cy="18" r="3" />
          <circle cx="16" cy="16" r="3" />
        </svg>;
    }
    return null;
  };
  return <span aria-label={`Supported modalities: ${modalities.join(", ")}`} role="group" style={{
    display: "inline-flex",
    alignItems: "center",
    gap: "0.5rem"
  }}>
      {modalities.map(modality => <span aria-label={modality} key={modality} role="img" style={{
    display: "inline-flex",
    flexShrink: 0
  }} title={modality}>
          {renderIcon(modality)}
        </span>)}
    </span>;
};

Response quality metrics help you measure how well your AI system answers user questions, follows instructions, and provides useful information in any setting — with or without RAG.

## Problems response quality metrics help you solve

* **You're not sure whether the model's answers are actually correct.** [Correctness](/concepts/metrics/response-quality/correctness) helps you spot factual mistakes in responses, even when there is no single reference answer.
* **You have reference answers and want to know how close the model gets.** [Ground Truth Adherence](/concepts/metrics/response-quality/ground-truth-adherence) tells you when a response is semantically equivalent to your gold answer and when it drifts away.
* **The model keeps ignoring or twisting your instructions.** [Instruction Adherence](/concepts/metrics/response-quality/instruction-adherence) highlights where responses fail to follow the structure, constraints, or style you asked for.

## Diagnose your response quality problem

Not sure which metric to start with? Walk through these symptoms to find the right one.

<AccordionGroup>
  <Accordion title="Responses contain factual errors" icon="triangle-exclamation">
    **Diagnosis:** The model is generating incorrect information — either from outdated training data or hallucination.

    **Start with:** [Correctness](/concepts/metrics/response-quality/correctness) to systematically identify factually wrong statements.

    **When to use this vs. Ground Truth Adherence:** Use Correctness when you don't have reference answers and want to catch general factual mistakes. Use Ground Truth Adherence when you have gold-standard answers to compare against.
  </Accordion>

  <Accordion title="Responses don't match expected answers" icon="not-equal">
    **Diagnosis:** You have reference answers (from experts, previous systems, or test datasets) and the model's outputs don't align with them.

    **Start with:** [Ground Truth Adherence](/concepts/metrics/response-quality/ground-truth-adherence) to measure semantic similarity to your gold answers.

    **Note:** This metric requires ground truth data, so it's primarily used in experiments and test suites, not real-time production monitoring.
  </Accordion>

  <Accordion title="The model ignores my prompt rules" icon="ban">
    **Diagnosis:** You've specified constraints (format, length, tone, prohibited topics) but the model keeps violating them.

    **Start with:** [Instruction Adherence](/concepts/metrics/response-quality/instruction-adherence) to detect when responses break your prompt's rules.

    **Common instruction failures:** Ignoring format requirements (JSON, bullets, tables), exceeding length limits, using wrong tone, mentioning prohibited topics, skipping required elements.
  </Accordion>
</AccordionGroup>

<Warning title="Common pitfall">
  **High Correctness + Low Instruction Adherence?** The model knows the right answer but isn't presenting it the way you asked. This is a prompt engineering issue — your instructions may need to be more explicit or positioned differently (system prompt vs. user message).
</Warning>

<Tip title="Response Quality vs. RAG metrics">
  Response Quality metrics work with or without retrieved context. If you're building a RAG system, combine these with [RAG metrics](/concepts/metrics/rag/rag-overview) — use RAG metrics to evaluate retrieval and grounding, and Response Quality metrics to evaluate factual accuracy and instruction-following.
</Tip>

Below is a quick reference table of these Response Quality metrics:

| Name                                                                                | Description                                                                                                                                                                 | Supported Nodes | Modalities                                                    | When to Use                                                                            | Example Use Case                                                                                    |
| :---------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------- | :------------------------------------------------------------ | :------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------- |
| [Ground Truth Adherence](/concepts/metrics/response-quality/ground-truth-adherence) | Measures how well the response aligns with established ground truth.<br /><br />This metric is only available for experiments as it needs ground truth set in your dataset. | Trace           | <ModalityIcons modalities={["Text", "Image/PDF", "Audio"]} /> | When evaluating model responses against known correct answers.                         | A customer service AI that must provide accurate product specifications from an official catalog.   |
| [Correctness (factuality)](/concepts/metrics/response-quality/correctness)          | Evaluates the factual accuracy of information provided in the response.                                                                                                     | LLM span        | <ModalityIcons modalities={["Text", "Image/PDF", "Audio"]} /> | When accuracy of information is critical to your application.                          | A medical information system providing drug interaction details to healthcare professionals.        |
| [Instruction Adherence](/concepts/metrics/response-quality/instruction-adherence)   | Assesses whether the model followed the instructions in your prompt template.                                                                                               | LLM span        | <ModalityIcons modalities={["Text"]} />                       | When using complex prompts and need to verify the model is following all instructions. | A content generation system that must follow specific brand guidelines and formatting requirements. |

***

## Next steps

* [Back to Metrics Overview](/concepts/metrics/overview)
* [Compare all metrics](/concepts/metrics/metric-comparison)