When:
Wednesday, October 30, 2024
5 to 6 p.m. Central Time
Cost:
STC coalition community members* – FREE
Students – FREE
Other STC members – $10
Non-members – $20
* This webinar is presented by a coalition of the following STC communities: Carolina Chapter, Chicago Chapter, DC-Baltimore Chapter, Florida Chapter, Michigan Great Lakes Chapter, Accessibility Special Interest Group (SIG), Instructional Design and Learning SIG, and Technical Editing SIG. Members of these communities can register free.
Large Language Models (LLMs) have a knowledge problem: Their training data is often out of date, and the information we want to leverage often isn’t included in the training data in the first place. Retrieval-Augmented Generation (RAG) is an approach to dynamically give LLMs the information we need them to have right when we need them to have it. Want an LLM to know about your products, procedures, or users? RAG is the solution.
But how do documents affect RAG? Document content, its formatting, and how it’s processed all impact whether the LLM responds with knowledge and (reasonable) confidence or whether the response is full of hallucinations. Come learn about RAG, how technical communicators can make use of it, how our documents affect RAG performance, and what we can do to make sure our users (and our LLMs) get the content they need when they need it.
About Our Speaker:
Technical writer by day and engineer by night, Manny Silva is Head of Documentation at Skyflow, the creator of Docs as Tests, and the creator of Doc Detective. He’s passionate about intuitive and scalable developer experiences and likes diving into the deep end as the 0th developer.
As always, special thanks to our chapter’s Friends of STC Chicago sponsors:
The LavaCon Conference on Content Strategy and TechComm Management
Add Comment