Prompt Engineering
The practice of designing and refining text inputs to effectively guide AI models toward desired outputs.
Token
The basic units that language models process, typically words, subwords, or punctuation marks.
Zero-Shot Learning
A model's ability to perform tasks it wasn't explicitly trained on, using only the prompt for guidance.
Few-Shot Learning
Providing a small number of examples in the prompt to guide the model's response format and content.
Context Window
The maximum amount of text (in tokens) a model can process in a single request.
Temperature
A parameter controlling randomness in model outputs, with lower values being more deterministic.
Top-p (Nucleus Sampling)
Limits token selection to the most probable options that cumulatively reach a certain probability threshold.
Fine-Tuning
Training a pre-trained model on a specific dataset to specialize its capabilities for particular tasks.
Embedding
Numerical representations of text that capture semantic meaning in a high-dimensional space.
Attention Mechanism
A model component that determines which parts of the input are most relevant for each output element.
Transformer
The neural network architecture that underlies most modern language models, using attention mechanisms.
Hallucination
When a model generates false or misleading information that appears plausible but is factually incorrect.
In-Context Learning
A model's ability to adapt its behavior based on examples and instructions provided within the prompt.
Chain-of-Thought
Prompting technique that encourages models to show their reasoning steps before providing an answer.
Retrieval-Augmented Generation (RAG)
Combining language models with external knowledge retrieval to produce more factual responses.
Bias
Systematic favoring of certain groups, perspectives, or outcomes in model outputs based on training data.
Alignment
Techniques for ensuring AI systems behave in accordance with human values and intentions.
Emergent Abilities
Capabilities that appear in large models without explicit training, such as reasoning or translation.
Scaling Laws
Predictable relationships between model size, dataset size, and performance improvements.
Instruction Tuning
Training models to better follow natural language instructions through specialized datasets.
Anthropomorphism
Attributing human characteristics, emotions, or intentions to AI systems.
Latent Space
High-dimensional representation space where models encode semantic relationships between concepts.
Pre-training
Initial training phase where models learn general language patterns from large text corpora.
Overfitting
When a model performs well on training data but poorly on new, unseen examples.
Transfer Learning
Applying knowledge gained from one task to improve performance on a related task.
Multimodal
Models that can process and generate multiple types of data, such as text, images, and audio.
Few-Shot Chain-of-Thought
Combining few-shot examples with chain-of-thought reasoning to solve complex problems.
Self-Attention
Mechanism allowing models to weigh the importance of different input elements relative to each other.
Decoder-Only
Model architecture that generates text sequentially, predicting one token at a time based on previous tokens.
Prompt Injection
Malicious manipulation of prompts to override intended model behavior or extract sensitive information.