# Is RLHF like fine-tuning a classification model at the end of each generation?

**URL:** <https://community.deeplearning.ai/t/is-rlhf-like-fine-tuning-a-classification-model-at-the-end-of-each-generation/375897>\
**Category:** Generative AI with Large Language Models\
**Tags:** week-module-3\
**Created:** [July 6, 2023, 12:09pm UTC](https://community.deeplearning.ai/t/is-rlhf-like-fine-tuning-a-classification-model-at-the-end-of-each-generation/375897 "2023-07-06T12:09:51Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Paramdeep](https://avatars.discourse-cdn.com/v4/letter/p/ba9def/32.png) [@Paramdeep](https://community.deeplearning.ai/u/Paramdeep)\
**Post date:** [July 6, 2023, 12:09pm UTC](https://community.deeplearning.ai/t/is-rlhf-like-fine-tuning-a-classification-model-at-the-end-of-each-generation/375897/1 "2023-07-06T12:09:51Z")

</div>

The RLHF is essentially selecting an output from a prompt (from multiple available options). Can this be treated like a classification model at the end of each prompt generation?

Just like we had prompt fine-tuning, is it possible to update the model with this classification model?

---

<div class="post-metadata">

**Author:** ![Atharva\_Divekar](https://avatars.discourse-cdn.com/v4/letter/a/e480ec/32.png) [@Atharva\_Divekar](https://community.deeplearning.ai/u/Atharva_Divekar)\
**Post date:** [July 8, 2023, 2:43pm UTC](https://community.deeplearning.ai/t/is-rlhf-like-fine-tuning-a-classification-model-at-the-end-of-each-generation/375897/2 "2023-07-08T14:43:33Z")

</div>

Yes, the RLHF can be treated like a classification model at the end of each prompt generation. It is possible to update the model with this classification model just like we had prompt fine-tuning.