Large language models (LLMs) such as ChatGPT has a tendency to sometimes, very confidently, state wrongful statements and facts that does not align with reality. This is a problem that is inherent in LLMs. When using AI in education this is a very obvious problem, students should learn facts and not misinformation. Is there a solution to the problem? As of now no one has solved the problem fully but one can drastically reduce the amount of hallucinations from LLMs. One such solution is using Retrieval Augmented Generation (RAG).

Retrieval Augmented Generation at it’s very core

At it’s very core RAG is really simple: from a user perspective it’s just like copy pasting relevant data into your chat message. Let’s say that you have a niche subject that the LLM hasn’t been trained on, it’s going to do it’s best to find a solution for you that it thinks is correct but might be terribly wrong. What you could do to mitigate this is to provide the AI with context, i.e., text relevant to what you are asking it about. As efficient human beings we don’t want to do this manually! So what RAG is doing is it is finding relevant paragraphs from your documents and copy pastes this into your chat message.

This is RAG at it’s very core but it does not stop there. You can do way more advanced stuff with RAG to make sure that you really do get the most relevant text retrieved. This will be further discussed in later articles, be sure to stick around and sign up to our newsletter (below!).

On Retinello premium users can upload and save their documents. These will then be transformed into vectors and stored in a vector database. Without going into much technical detail: vectors are used to calculate the distance between two different pieces of text to make sure that you get the most relevant text retrieved. OK so it’s stored in a vector database, what next?

You can have a normal “chat with pdf”-style of service where you just chat directly to your document, where every single chat message can be turned into flashcards! You can also attach your documents to your decks. Why? It is because when you study using interactive learning you want to keep the model informed of what you are studying, so when you have a document attached to your deck it will do RAG for you in the background when you’re studying using interactive learning!

What Retrieval Augmented Generation (RAG) is, how it can make large language models hallucinate less and how we are using this on Retinello.

What is Retrieval Augmented Generation?

Spaced repetition (SR) is a scientifically proven learning technique that involves reviewing information at increasing intervals to improve long-term retention of the material. The principle behind it is relatively straightforward: instead of trying to learn or memorize something all at once and cramming it into your brain, spaced repetition leverages the psychological spacing effect, where learning is more efficient when spread out over time. Using spaced repetition, you can escape your bad study habits, and avoid pulling all-nighters the day before your exam!

How does spaced repetition work in practice?

In practice, you might review something you've learned after one day, then three days, then a week, then a month, and so on. Each interval is longer than the last, provided you keep remembering the information. This method is incredibly effective because it is believed to optimize the strengthening of memory traces in the brain, making recall easier and more reliable over time.

An illustration showing how reviewing at different intervals increases memory retention.

Spaced repetition allows your to not only memorize for your exams, but also to memorize for life, and the best part is that it can be used in practically any learning context, such as medicine, history, or even maths!

How is spaced repetition used on Retinello?

On Retinello, we have implemented our own variant of a spaced repetition algorithim which all of the learning on the platform is based on. It does not matter whether you're using our spaced repetition or interactive learning feature for memorizing your flashcards, our algorithim will determine the optimal time interval for the next review based on how well you graded yourself when reviewing, or based off of an underlying score provided by our AI-teacher when using the interactive learning feature.

An illustration of how flashcards are spaced in time on Retinello based on how hard they are.

Flashcards that you struggle with will appear sooner in your reviews, and ones that you master later. All in order to maximize the efficiency of your learning alongside our AI-empowered flashcard generation tools.

Want to try out Spaced Repetition? You can do so on Retinello for free!

An article about what spaced repetition is, why it is so great for learning new things, and how it is used on Retinello.

Ready to
level up
your
learning?

Welcome to Retinello

Recent updates

What is Retrieval Augmented Generation?

Spaced Repetition And Why It Is So Great For Learning!

Ready to level up your learning?

Welcome to Retinello

Recent updates

What is Retrieval Augmented Generation?

Spaced Repetition And Why It Is So Great For Learning!

Ready to
level up
your
learning?