Find a term
Build a practical understanding of language models, prompts, tokens, and context. Focus on the concepts that affect real applications and engineering workflows.
Terms beginning with P
16 termsPolicy gradient
Policy gradient is a language-model concept about evaluation design and failure analysis. It names a mechanism, representation, training practice, or operational behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPosition embedding
Position embedding is a language-model concept about context selection and limits. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPosition interpolation
Position interpolation is a language-model concept about evaluation design and failure analysis. It names a mechanism, representation, training practice, or operational behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPreference model
Preference model is a language-model concept about evaluation design and failure analysis. It names a mechanism, representation, training practice, or operational behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrefix-constrained decoding
Prefix-constrained decoding is a language-model concept about context selection and limits. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrompt compilation
Prompt compilation is a language-model concept about generation behavior and sampling. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrompt compression
Prompt compression is a language-model concept about context selection and limits. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrompt engineering
Prompt engineering is the practice of designing and testing instructions, examples, context, and output requirements that guide a language model toward a useful result. It is an iterative engineering activity supported by evaluation and observability.
LLM fundamentalsPrompt injection
Prompt injection is an attack or unintended instruction that causes a language model to treat untrusted content as higher-priority guidance. It can redirect an application, expose data, or trigger tools in ways the developer did not intend.
LLM fundamentalsPrompt injection defense
Prompt injection defense is a language-model concept about instruction design and control. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrompt registry
Prompt registry is a language-model concept about representation and similarity. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrompt robustness
Prompt robustness is a language-model concept about representation and similarity. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrompt template
Prompt template is a language-model concept about generation behavior and sampling. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrompt variable
Prompt variable is a language-model concept about context selection and limits. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsPrompt version
Prompt version is a language-model concept about instruction design and control. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.
LLM fundamentalsProximal policy optimization
Proximal policy optimization is a language-model concept about serving behavior and operational tradeoffs. It names a mechanism, representation, training practice, or operational behavior that can change how an AI system processes input and produces output.
LLM fundamentals