Save this video free

UUtah CS 6340 NLP | Fall 2026 | RAG & ODQA-pipeline training

UofU Data Science · 54:43 · Watch on YouTube

Part of University of Utah CS 6340. See all 19 lectures and search them

These notes were made with YouTube Collector. Paste any YouTube link and get the same: a summary, chapters and a searchable transcript.

Overview

The lecture explains how retrieval-augmented generation (RAG) supports open-domain question answering by grounding an LLM’s answer in retrieved documents, then examines practical constraints such as context limits, position bias, and conflicts with parametric knowledge. It compares four ways to train retrieval and answer components, emphasizing in-batch joint training with a relevant document and 10,000 sampled negatives as a scalable compromise, while recommending simple baselines before more complex methods.

Key takeaways

Chapters

0:00 RAG Grounds Open-Domain Answers in Retrieved Documents
4:34 Context Windows, RoPE, and Conversation Compaction
9:45 Prompt Position Bias and Conflicts with Parametric Knowledge
13:21 Why Joint Training Could Improve RAG Pipelines
20:40 Separate Training and Its Retrieved-Document Mismatch
29:00 Frozen Components and Scalable In-Batch Joint Training
38:03 Choose RAG Training Methods by Complexity and Performance
43:20 Extraction Versus Generation, Latency, Cost, and Privacy
49:48 Review of Dense Retrieval, ODQA, and Training Strategy
53:06 Hugging Face and Legal Retrieval Resources

Keep these chapters and the full searchable transcript in your own library.

Transcript excerpt

0:00 Sorry I'm late. It's one of those days. I will also need to leave today right after the class. So if you have any questions, I usually stick around, but please come to the office hours. Happy to answer them there. Are there any questions before we continue where we left things off last time? Okay, seems like we are good. Um all right so we are continuing our uh you know learning about question answering and last time we came to about a point where I started to introduce uh retrieval augmented generation. Um and just a kind of reminder we have these three options for how to go about open uh domain uh question answering. Uh two of them uh are pipeliny. They have first

0:51 the retrieval stage and after we retrieve uh certain relevant documents, we answer some question in the context of those documents. And we have seen an approach where we extract the answer. Uh and today we are talking about uh an approach where we generate the uh answer. Um so um why why I I brought up this question a few times. Why wouldn't we just generate the answer immediately without having uh the retrieval stage? And uh the main main uh argument here is that you might have settings where you cannot re not rely on so-called parametric knowledge of the model. Meaning model had acquired a lot of knowledge during pre-training and those are those those facts are stored in the

1:39 weights of the model and this is why models are capable of answering all sorts of uh question without you know retrieving context but if you have a special setup where your data or data domain isn't super well represented on the um internet then you shouldn't expect that the model will

This is the start of the transcript. Save this video free for the whole transcript, searchable and time-coded.

In this course

Related notes

Summary, takeaways, and chapters were generated by AI from the video's transcript and may contain errors. The video belongs to its creator, UofU Data Science.

Want the full transcript?

Save this video in YouTube Collector to get its complete searchable transcript, your own AI summaries, and a library that keeps every video you collect in one place.