---
title: Evaluate generated answers
slug: p5db0063
canonical_url: https://docs.coveo.com/en/p5db0063/
collection: knowledge-hub
source_format: adoc
---
# Evaluate generated answers
> **Important**
>
> The Coveo Knowledge Hub is currently available as a beta to early-access customers only.
> Contact your Customer Success Manager for early access to this feature.

Evaluating the answers that are generated by [Relevance Generative Answering (RGA)](https://docs.coveo.com/en/nbtb6010/) is a crucial part of your [RGA](https://docs.coveo.com/en/nbtb6010/) implementation, just as with any generative answering system.

At a basic level, [RGA](https://docs.coveo.com/en/nbtb6010/) relies on data and algorithms to generate answers.
Evaluating the answers that are generated for specific user queries helps you assess the effectiveness of your [RGA](https://docs.coveo.com/en/nbtb6010/) implementation in relation to your dataset.
Evaluating the generated answers is an important step when testing your [RGA](https://docs.coveo.com/en/nbtb6010/) implementation in a pre-production environment.
Post-production evaluations are equally valuable, as they help you fine-tune and improve your implementation as your dataset evolves.

## How to evaluate generated answers

How does one effectively evaluate a generated answer?
Providing and gathering feedback on a generated answer's perceived correctness, relevance, and usefulness is a good first step, but it doesn't offer insights that you can use to improve your generative answering implementation.
For example, if a generated answer is flagged as incorrect or irrelevant, troubleshooting the issue would be difficult without a more in-depth analysis of how the answer was generated.
The same applies to a generated answer that's considered correct but not based on the most relevant or up-to-date content.

An effective answer evaluation strategy, therefore, should include not only a review of the generated answer but also an examination of the segments of text (chunks) that were used to generate that answer.

> **You're here**
>
> In the [improving your RGA implementation through answer evaluation](https://docs.coveo.com/en/p58d0270#improve-your-rga-implementation-through-answer-evaluation) workflow, an effective answer evaluation strategy includes reviewing the feedback to identify the answers that need your attention, and inspecting the chunks that were used to generate the answers.
> 
> ![Coveo Knowledge Hub RGA answer evaluation step](:https://docs.coveo.com/en/assets/images/leverage-machine-learning/knowledge-hub-flow-eval-step.png)

Use the following [Knowledge Hub](https://docs.coveo.com/en/p59f0295/) tools to evaluate your [RGA](https://docs.coveo.com/en/nbtb6010/)-generated answers:

* Use the Answer Manager to [review the user feedback](https://docs.coveo.com/en/p5db0180/) collected for the generated answers.

> **Important**
>
> For feedback to appear in the Answer Manager, you must [associate an answer configuration](https://docs.coveo.com/en/p5db9314/) with your [RGA](https://docs.coveo.com/en/nbtb6010/)-enabled search interface.

> **Note**
>
> Feedback is collected when the thumbs-up or thumbs-down icon is clicked in the [RGA component](https://docs.coveo.com/en/nb6a0037#rga-component-features) in the search interface.
> Feedback is typically provided by search interface users, but it can also be provided by a subject matter expert in your organization tasked with testing the [RGA](https://docs.coveo.com/en/nbtb6010/) implementation.

* Use the Chunk Inspector to [inspect the chunks that [RGA](https://docs.coveo.com/en/p5dc0110/)(https://docs.coveo.com/en/nbtb6010/) used to generate a specific answer].
This is especially useful when evaluating answers with negative feedback or answers that have been flagged as needing improvement.

> **Tip**
>
> Based on the insights you gain from reviewing the feedback and chunk information, you can then choose to [create answer rules, modify your content, and modify your RGA implementation configuration](https://docs.coveo.com/en/p5db0550/) to improve your [RGA](https://docs.coveo.com/en/nbtb6010/) implementation.