Re:Enhancing Frame Detection with Retrieval Augmented Genera...
by nthingtohide on Tuesday March 04, 2025 @11:51AM
(#43257163)
I have this very stupid question and I haven't seen it answered anywhere.
Let's say LLM while training is ingesting a very long book.
The name of the author of the book would appear at the very beginning.
While inference, how does the llm determine that the last chapter of the book is written by so and so author and hence that chunk should be near that author's style.
Re:Enhancing Frame Detection with Retrieval Augmented Genera...
by visarga on Tuesday March 04, 2025 @11:59AM
(#43257252)
The information is probably lost, training on very long inputs is expensive, we usually train on short inputs and only send longer ones at the end. So the author name would not appear together with all the chunks unless it appears on every page in the header, assuming the headers are not stripped out first.
Re:Enhancing Frame Detection with Retrieval Augmented Genera...
by nthingtohide on Tuesday March 04, 2025 @11:29PM
(#43262791)
I am wondering the same techniques we use to augment chunks for RAG also the same technique used to augment training data with rich metadata. A preprocessing step which ensures metadata rich text for creating foundational models.
The idea of detecting frames and using them to tease out the implicit meaning from text is quite nice. It seems there is a lot more to discover about using LLMs prior to RAG. Text is like code, you can't know what it does untill you run it, and in this case, until you annotate it. For example "10+10" won't embed close to "20". And "The fifth letter in this string" won't retrieve "f" by emmbedding similarity.