Unit 2: Large Language Models

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/16

encourage image

There's no tags or description

Looks like no tags are added yet.

Last updated 1:37 PM on 10/13/26
Name
Mastery
Learn
Test
Matching
Spaced
Call with Kai
Chat

No analytics yet

Send a link to your students to track their progress

17 Terms

1
New cards

Give an example of a search engine.

Google

2
New cards

Deine search engine.

A software system that provides hyperlinks to web pages and other relevant information on the web in response to a user's query.

3
New cards

Give an example of an LLM.

ChatGPT

4
New cards

Deine LLM.

A type of artificial intelligence trained to predict what word(s) are most likely to come next in a sequence of text.

5
New cards

What is another word for "tokens"?

Words

6
New cards

What does LLM stand for?

Large Language Model

7
New cards

Define model.

A mathematical function produced through machine learning that learns relationships between inputs and outputs in order to generalize patterns to new data for prediction.

8
New cards

What is step 1 in the LLM process?

Feature detection

9
New cards

Define feature detection.

Use the prompt's topic and style. Keep the response on topic and in the correct style.

10
New cards

What is step 2 in the LLM process?

Word matching

11
New cards

Define word matching.

Recognize similar language patterns. Use learned language patterns to activate relevant ideas.

12
New cards

What is step 3 in the LLM process?

Voting

13
New cards

Define voting.

Calculate which possible next word is most likely. Choose the word.

14
New cards

What is step 4 of the LLM process?

Word guessing

15
New cards

Define word guessing.

Predict the next word. Build the response, one word at a time.

16
New cards

Define a lie.

A false statement made on purpose to trick someone.

17
New cards

Define hallucination.

An AI source's confident creation of false or misleading information while presenting it as a fact.