Advanced Topics in Computer Science/Business Lecture on 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

1/9

flashcard set

Earn XP

Description and Tags

A series of flashcards covering key concepts from a lecture on Large Language Models in advanced computer science and business, with a focus on problem-solving strategies and evaluation metrics.

Last updated 5:41 PM on 4/13/26
Name
Mastery
Learn
Test
Matching
Spaced
Call with Kai

No analytics yet

Send a link to your students to track their progress

10 Terms

1
New cards

RAG architecture

Retrieval-Augmented Generation architecture designed to enhance the capabilities of language models by incorporating retrieval of additional information.

2
New cards

LLM

Large Language Model, a type of AI designed to understand and generate human-like text through machine learning techniques.

3
New cards

Rouge

A set of metrics used to evaluate automatic summarization and machine translation by comparing generated output against reference texts.

4
New cards

Poe

An online platform enabling users to interact with various AI language models for tasks such as summarization.

5
New cards

Decision Tree Analysis

A machine learning technique used to visualize and analyze decision-making processes based on data attributes.

6
New cards

Embedding Vector

A mathematical representation of text data in a high-dimensional space useful for various natural language processing tasks.

7
New cards

Faiss

Facebook AI Similarity Search, a library for efficient similarity search and clustering of dense vectors.

8
New cards

Prompt Engineering

The process of designing and optimizing input messages used to instruct LLMs to generate desired outputs.

9
New cards

CADET

Customer Agent Decision Tree, a proposed framework for agent-based modeling of customer behavior.

10
New cards

Mistral and Llama

Different large language models compared based on their performance in understanding and generating text.