> For the complete documentation index, see [llms.txt](https://docs.raga.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.raga.ai/ragaai-catalyst/ragaai-metric-library/text-summarization/summary-consistency.md).

# Summary Consistency

Measure whether summaries stay faithful to the original text. Spot inconsistencies and improve alignment with source content.

**Objective:** 

Summary Consistency evaluates the factual alignment between the generated summary and the source content. It checks if the summary maintains the same facts, figures, and core messages as the input without introducing any hallucinations or errors. This metric is crucial for ensuring that no factual distortions occur when compressing the information.

**Required Columns in Dataset:**

`LLM Summary`, `Original Document`

**Interpretation:**

* **High values**: Indicate that the summary is factually accurate and reflects the original information without alterations.
* **Low values**: Suggest factual inconsistencies, errors, or hallucinations introduced in the summary.

**Execution via UI:**

<figure><img src="https://1811327582-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYbIiNdp1QbG4avl7VShw%2Fuploads%2FwxhbG1zXzPxWq2VAWnop%2Fimage.png?alt=media&amp;token=25ff349e-2816-402f-ae77-20a67778775e" alt=""><figcaption></figcaption></figure>

**Execution via SDK:**

```python
metrics=[
    {"name": "Summary Consistency", "config": {"model": "gpt-4o-mini", "provider": "openai"}, "column_name": "your-text", "schema_mapping": schema_mapping}
]
```