LLM Vocabulary & Terms

Core Concepts

Foundation Model

LLM designed to generate and understand human-like text across a wide range of use-cases. Learn more

Transformer

A popular LLM design known for its attention mechanism and parallel processing abilities. Learn more

Prompting

Providing carefully crafted inputs to an LLM to generate desired outputs. Learn more

Context-Length

Maximum number of input words/tokens an LLM can consider when generating an output. Learn more

Few-Shot Learning

Providing very few examples to an LLM to assist it in performing a specific task. Learn more

Zero-Shot Learning

Providing only task instructions to the LLM, relying solely on its pre-existing knowledge. Learn more

RAG Components

RAG (Retrieval-Augmented Generation)

Appending retrieved information to improve LLM response. Learn more

Knowledge Base (KB)

Collection of documents from which relevant information is retrieved in RAG. Learn more

Vector Database

Stores vector representations of the KB, aiding the retrieval of relevant information in RAG. Learn more

Chunking

Breaking the KB into smaller pieces for efficient storage and retrieval during RAG. Learn more

Indexing

Organizing and storing KB chunks in a structured manner for efficient retrieval. Learn more

Embedding Model

An LLM that converts KB text chunks into numerical format called vectors/embeddings. Learn more

Finding the most relevant KB chunks based on vector similarity scores for a given input query. Learn more

Retrieval

Approach used to rank and fetch KB chunks from the vector search. This will serve as additional context for the LLM. Learn more

Agent Concepts

AGI (Artificial General Intelligence)

Artificial General Intelligence aims to create machines that can learn and reason like humans across various tasks.

LLM Agent

LLM applications that can execute complex tasks by combining LLMs with modules like planning and memory. Learn more

Agent Memory

A module that stores the agentโ€™s past experiences and interactions with the user and environment. Learn more

Agent Planning

Module that divides the agentโ€™s tasks into smaller steps to address the userโ€™s request efficiently. Learn more

Function Calling

Ability of LLM agents to request information from external tools and APIs in order to execute a task. Learn more

Ethics & Governance

LLM Bias

Systematic prejudices in the LLMโ€™s predictions, often stemming from training data.

XAI

Explainable AI. Making the modelโ€™s outputs understandable and transparent to humans.

Responsible AI

Ensuring ethical, fair, and transparent development and use of AI systems.

AI Governance

Legal policies & frameworks that regulate the development & deployment of AI systems.

Compliance

Ensuring adherence to legal requirements in the development & deployment of AI systems.

GDPR

General Data Protection Regulation protecting individualsโ€™ privacy rights and governing data handling in the EU.

Alignment

Ensuring that the outputs of LLMs are consistent with human values and intentions.

Model Ethics

Ensuring ethical behavior (transparency, fairness, accountability etc.) when deploying public-facing AI.

PII

Personally Identifiable Information. Should not be stored or used without proper processes and user consent.

LLMOps

Managing and optimizing operations for LLM deployment and maintenance. Learn more

Privacy-preserving AI

Methods to train and use LLMs while safeguarding sensitive data privacy.

Adversarial Defense

Methods to prevent malicious attempts to manipulate LLMs, ensuring their security.

Security

Adversarial Attacks

Deliberate attempts to trick LLMs with carefully crafted inputs, causing them to make mistakes.

Black-Box Attacks

Trying to attack an LLM without knowing its internal workings or parameters.

White-Box Attacks

Attacking an LLM with full knowledge of its internal architecture and parameters.

Vulnerability

Weaknesses or flaws in LLMs that can be exploited for malicious purposes.

Deep-fakes

Synthetic media generated by LLMs, often used to create realistic but fake images or videos.

Jailbreaking

Attempting to bypass security measures around an LLM to make it produce unsafe outputs.

Prompt Injection

Hijacking the LLMโ€™s original prompts to make it perform unintended tasks.

Prompt Leaking

Tricking an LLM to reveal information from its training or inner workings.

Red-Teaming

Assessing the security and robustness of LLMs through simulated adversarial attacks.

Robustness

The ability of an LLM to perform accurately despite encountering adversarial inputs.

Watermarking

Embedding hidden markers into LLM-generated content to track its origin or authenticity.

Learning Paradigms

Unsupervised Learning

Learning patterns and structures from data without specific guidance or labels.

Supervised Learning

Learning from labeled examples & associating inputs with correct outputs.

Reinforcement Learning

Learning through trial and error, with rewards or penalties based on generated outputs.

Meta-Learning

Learning to learn by extracting general knowledge from diverse tasks and applying it to new ones.

Multi-task Learning

Learning to perform multiple tasks & sharing knowledge between related tasks for better performance.

Zero-Shot Learning

Providing only task instructions to the LLM relying solely on its pre-existing knowledge. Learn more

Few-Shot Learning

Learning from a small number of examples for new tasks and adapting quickly with minimal data. Learn more

Online Learning

Continuously learning from incoming data streams and updating knowledge in real-time.

Continual Learning

Learning sequentially from a stream of tasks or data without forgetting previously learned knowledge.

Federated Learning

Training across multiple decentralized devices without sharing raw data, preserving user privacy.

Adversarial Learning

Training against adversaries or competing models to improve robustness and performance.

Active Learning

Interacting with humans or the environment to select and label the most useful data for training.

Additional Resources

Types of LLMs Lingo


๐Ÿš€ 10K+ page views in last 7 days
Developer Handbook 2025 ยฉ Exemplar.