---
title: Corrections
description: Capture improved versions of LLM outputs directly in traces and observations to build better datasets and drive continuous improvement.
sidebarTitle: Corrections
---

# Corrected Outputs

Corrections allow you to capture improved versions of LLM outputs directly in trace and observation views. Domain experts can document what the model should have generated, creating a foundation for fine-tuning datasets and continuous improvement.

  ![Corrected output with diff view](/images/docs/corrections-diff-view.png)

## Why Use Corrections?

- **Domain expert feedback**: Subject matter experts provide what the model should have output based on their expertise
- **Fine-tuning datasets**: Export corrected outputs alongside original inputs to create high-quality training data from production traces
- **Quality benchmarking**: Compare actual vs expected outputs across your production traces to identify systematic issues
- **Human-in-the-loop workflows**: Capture corrections during review processes, especially useful in [annotation queues](/docs/evaluation/evaluation-methods/annotation-queues)

## How It Works

Add corrected outputs to any trace or observation through the UI or API. Corrections appear alongside the original output with a diff view showing what changed. Each trace or observation can have one corrected output.

## Adding Corrections

<LangTabs items={["Langfuse UI", "API/SDK"]}>

<Tab>

### Via the UI

Navigate to any trace or observation detail page:

1. Find the **"Corrected Output"** field below the original output
2. Click to add or edit the correction
3. Enter the improved version of the output
4. Toggle between **JSON validation mode** and **plain text mode** to match your data format
5. View the **diff** to compare original vs corrected output

  ![Adding a correction in the UI](/images/docs/corrections-add-ui.png)

The editor auto-saves as you type and provides real-time validation feedback in JSON mode.

</Tab>

<Tab>

### Via API/SDK

Corrections are created as scores with `dataType: "CORRECTION"` and `name: "output"`.

<Tabs items={["Python", "TypeScript", "HTTP"]}>
<Tab>

```python
from langfuse import Langfuse

langfuse = Langfuse()

# Add correction to a trace
langfuse.create_score(
    trace_id="trace-123",
    name="output",
    value="The corrected output text here",
    data_type="CORRECTION"
)

# Add correction to an observation
langfuse.create_score(
    trace_id="trace-123",
    observation_id="obs-456",
    name="output",
    value="The corrected output text here",
    data_type="CORRECTION"
)
```

</Tab>
<Tab>

```typescript
import { LangfuseClient } from "@langfuse/client";

const langfuse = new LangfuseClient();

// Add correction to a trace
langfuse.score.create({
  traceId: "trace-123",
  name: "output",
  value: "The corrected output text here",
  dataType: "CORRECTION"
});

// Add correction to an observation
langfuse.score.create({
  traceId: "trace-123",
  observationId: "obs-456",
  name: "output",
  value: "The corrected output text here",
  dataType: "CORRECTION"
});
```

</Tab>
<Tab>

```bash
curl -X POST https://cloud.langfuse.com/api/public/scores \
  -H "Content-Type: application/json" \
  -H "Authorization: Basic <base64_encoded_credentials>" \
  -d '{
    "traceId": "trace-123",
    "observationId": "obs-456",
    "name": "output",
    "value": "The corrected output text here",
    "dataType": "CORRECTION"
  }'
```

</Tab>
</Tabs>

</Tab>

</LangTabs>

## Fetching Corrections

Corrections are stored as scores and can be fetched programmatically to build datasets or analyze model performance. Filter the [Scores API](/docs/api-and-data-platform/features/scores-api) by `dataType=CORRECTION`. The corrected output is in the `value` field.

<Tabs items={["Python", "TypeScript", "HTTP"]}>
<Tab>

```python
from langfuse import get_client

langfuse = get_client()

corrections = langfuse.api.scores_v3.get_many_v3(
    data_type="CORRECTION",
    fields="subject,details",
)
```

</Tab>
<Tab>

```typescript
import { LangfuseClient } from "@langfuse/client";

const langfuse = new LangfuseClient();

const corrections = await langfuse.api.scoresV3.getManyV3({
  dataType: "CORRECTION",
  fields: "subject,details",
});
```

</Tab>
<Tab>

```bash
curl -X GET "https://cloud.langfuse.com/api/public/v3/scores?dataType=CORRECTION&fields=subject,details" \
  -H "Authorization: Basic <base64_encoded_credentials>"
```

</Tab>
</Tabs>

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/docs/observability/features/corrections.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.