Eric - it sounds like we may be at about the same point: I am wanting to start working in the area of fine-tuning, specifically focusing on Chat-GPT generated data management plans that would then be revised by experts and used as a fine-tuning data corpus for (hopefully) improving the draft DMP language provided by Chat-GPT. This is part of a broader experimentation with DMP generation prompts derived from machine-readable DMP content.

Thanks,
Karl

Karl Benedict
Director of Research Data Services/ Director of IT
College of University Libraries and Learning Sciences
University of New Mexico

Office: Centennial Science and Engineering Library, Room L173

Make an Appointment: [log in to unmask]" target="_blank">https:[log in to unmask]

On 26 Feb 2024, at 14:05, Eric Lease Morgan wrote:

> [You don't often get email from [log in to unmask] Learn why this is important at https://aka.ms/LearnAboutSenderIdentification ]
>
>   [EXTERNAL]
>
> Who out here in Code4Lib Land is practicing with either one or both of the following things: 1) fine-tuning large-language models, or 2) retrieval-augmented generation (RAG). If there is somebody out there, then I'd love to chat.
>
> When it comes to generative AI -- things like ChatGPT -- one of the first things us librarians say is, "I don't know how I can trust those results because I don't know from whence the content originated." Thus, if we were create our own model, then we can trust the results. Right? Well, almost. The things of ChatGPT are "large language models" and the creation of such things are very expensive. They require more content than we have, more computing horsepower than we are willing to buy, and more computing expertise than we are willing to hire. On the other hand there is a process called "fine-tuning", where one's own content is used to supplement an existing large-language model, and in the end the model knows about one's own content. I plan to experiment with this process; I plan to fine-tune an existing large-language model and experiment with it use.
>
> Another approach to generative AI is called RAG -- retrieval-augmented generation. In this scenerio, one's content is first indexed using any number of different techniques. Next, given a query, the index is searched for matching documents. Third, the matching documents are given as input to the large-language model, and the model uses the documents to structure the result -- a simple sentence, a paragraph, a few paragraphs, an outline, or some sort of structured data (CSV, JSON, etc.). In any case, only the content given to the model is used for analysis, and the model's primary purpose is to structure the result. Compared to fine-tuning, RAG is computationally dirt cheap. Like fine-tuning, I plan to experiment with RAG.
>
> To the best of my recollection, I have not seen very much discussion on this list about the technological aspects of fine-tuning nor RAG. If you are working these technologies, then I'd love to hear from you. Let's share war stories.
>
> --
> Eric Morgan <[log in to unmask]>
> Navari Family Center for Digital Scholarship
> University of Notre Dame