# Collection Methods

* **Rating outputs**: People rate AI-generated content (good/bad, helpful/harmful, preferred/less preferred).
* **Pairwise comparisons**: Given two outputs, humans pick which is better.
* **Direct edits or suggestions**: Annotators or users improve the AI’s output (e.g., rewriting text or correcting errors).
* **Specialized feedback**: Domain experts (e.g., lawyers, doctors, teachers) review content for accuracy in specialized fields.
* Feedback is turned into training signals for techniques like **Reinforcement Learning from Human Feedback (RLHF)** or **Direct Preference Optimization (DPO)**.

<figure><img src="/files/hN6B1Gnrty0D7K9s1UdW" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://reppo-labs-xyz.gitbook.io/reppo-labs/protocol-mechanics/collection-methods.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.