AI Glossary: Letter "P"

Parameters are the internal configuration variables of an AI model that are learned automatically from training data. In a neural network, parameters consist of weights (which determine connection strength) and biases (which offset activation curves).

Parameter-Efficient Fine-Tuning (PEFT) is a collection of training methods designed to fine-tune large foundation models by adapting only a tiny subset of additional parameters, while freezing the base model's weights.

Perplexity is a core evaluation metric in natural language processing measuring how well a probability distribution or language model predicts a sample of text.

Pre-training is the initial phase of training an AI model on a massive general-purpose dataset (unsupervised or self-supervised), teaching the model basic syntax, grammar, and features before fine-tuning.

Precision (Positive Predictive Value) is a classification evaluation metric measuring the fraction of predicted positive examples that are actually correct, calculated as true positives divided by all predicted positives.

Preference Alignment refers to the training process of tuning a Large Language Model's conversational behavior to match human preferences regarding helpfulness, safety guidelines, and formatting style.

A Process Reward Model (PRM) is a reward system that scores each individual step or line of reasoning in a model's output, rather than just the final answer. This encourages models to follow correct logical steps and helps prevent hallucinations during complex tasks.

A Prompt is the textual, visual, or binary input submitted to a generative AI model to initiate and guide the generation of a specific response or action.

Prompt Caching is an optimization technique that stores prefix token representations of long prompts in memory, allowing subsequent API queries with the same prefix to reuse states, reducing latency and cost.

Prompt Compression is a optimization technique that filters out redundant tokens or words from a prompt while preserving its core semantic meaning. This saves context window space and lowers API costs.

Prompt Engineering is the practice of designing, structuring, and refining inputs (prompts) to get optimal, predictable outputs from generative AI models. It involves technique selection like chain-of-thought, few-shot prompting, and system routing.

Prompt Injection is a security vulnerability where a malicious user provides input that overrides the pre-configured system instructions or safety alignment filters of a Large Language Model, hijacking its control flow.

PyTorch is the dominant open-source machine learning framework developed by Meta AI research, widely used for building, training, and deploying deep learning models.