# RAD embedded retrieval + fine tuning OR retrieval assistant + fine tuning. What will be better to create a gpt to help lawyers draft arguments

**URL:** <https://community.openai.com/t/rad-embedded-retrieval-fine-tuning-or-retrieval-assistant-fine-tuning-what-will-be-better-to-create-a-gpt-to-help-lawyers-draft-arguments/584016>\
**Category:** Community\
**Tags:** fine-tuning, plugins, rag, assistants\
**Created:** [January 12, 2024, 10:54am UTC](https://community.openai.com/t/rad-embedded-retrieval-fine-tuning-or-retrieval-assistant-fine-tuning-what-will-be-better-to-create-a-gpt-to-help-lawyers-draft-arguments/584016 "2024-01-12T10:54:54Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![cyzgab](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/cyzgab/32/281690_2.png) [@cyzgab](https://community.openai.com/u/cyzgab)\
**Post date:** [January 12, 2024, 3:02pm UTC](https://community.openai.com/t/rad-embedded-retrieval-fine-tuning-or-retrieval-assistant-fine-tuning-what-will-be-better-to-create-a-gpt-to-help-lawyers-draft-arguments/584016/2 "2024-01-12T15:02:54Z")

</div>

> [@rithikchaudhary15050](#):
>
> teach the model of critical thinking

Generally, fine-tuning is to teach the model to reply in a specific way. Fine-tuning won’t be sufficient to teach the model “new content”.

That aside, what you’ve described for the fine-tuning examples, and the retrieval approach some sensible.

You could prototype with the assistants api first, though you won’t be able to use your finetuned model.

---

_[View the full topic](https://community.openai.com/t/rad-embedded-retrieval-fine-tuning-or-retrieval-assistant-fine-tuning-what-will-be-better-to-create-a-gpt-to-help-lawyers-draft-arguments/584016)._