> ## Documentation Index
> Fetch the complete documentation index at: https://docs.seekr.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Glossary

> Definitions of the terms used across SeekrGuard.

Each entry defines a SeekrGuard term and links to the guide where it is used in depth.

**Jump to:** [A](#a) · [B](#b) · [C](#c) · [D](#d) · [E](#e) · [J](#j) · [L](#l) · [M](#m) · [P](#p) · [R](#r) · [S](#s) · [T](#t) · [U](#u) · [V](#v)

## A

<a id="aggregation-method" style={{scrollMarginTop: "6rem"}} />

**aggregation method** – how a risk category combines its evaluators' scores into a single category score, such as a weighted average. Distinct from the method a risk profile uses to combine its categories. See [Build risk profiles](/guard/app/risk-profiles).

<a id="assistant-message" style={{scrollMarginTop: "6rem"}} />

**Assistant Message** – the message template that holds an [expected output](/guard/glossary#expected-output).

[↑ Back to top](/guard/glossary)

## B

<a id="bleu" style={{scrollMarginTop: "6rem"}} />

**BLEU** – a metric that scores how much of a model's output matches the expected output, counting runs of consecutive words. Higher scores mean the output stays closer to the reference wording. See [Create evaluators](/guard/app/evaluators).

[↑ Back to top](/guard/glossary)

## C

<a id="chat-history" style={{scrollMarginTop: "6rem"}} />

**Chat History** – the message template that holds [conversation history](/guard/glossary#conversation-history).

<a id="comparison" style={{scrollMarginTop: "6rem"}} />

**comparison** – a scoring of a single response by several evaluators and judge models, shown as a grid. By contrast, an examination runs over a dataset. See [Run comparisons](/guard/app/comparisons).

<a id="context" style={{scrollMarginTop: "6rem"}} />

**Context** – the message template that holds a [context input](/guard/glossary#context-input).

<a id="context-input" style={{scrollMarginTop: "6rem"}} />

**context input** – background or retrieved material supplied alongside the user's question, used in retrieval-augmented generation (RAG). When you upload a dataset, you map it to the **Context** template. See [Add and manage datasets](/guard/app/datasets).

<a id="conversation-history" style={{scrollMarginTop: "6rem"}} />

**conversation history** – prior turns of a multi-turn conversation included with an input. When you upload a dataset, you map it to the **Chat History** template. See [Add and manage datasets](/guard/app/datasets).

[↑ Back to top](/guard/glossary)

## D

<a id="dataset" style={{scrollMarginTop: "6rem"}} />

**dataset** – a collection of test inputs, and optionally expected answers, that you test models on. Each input can include a system prompt, user question, context, conversation history, and expected output. See [Add and manage datasets](/guard/app/datasets).

[↑ Back to top](/guard/glossary)

## E

<a id="evaluator" style={{scrollMarginTop: "6rem"}} />

**evaluator** – a scorer that grades a model's output on one dimension, such as accuracy, toxicity, or relevance. There are three types: LLM-as-a-Judge, rule-based, and statistical. See [Create evaluators](/guard/app/evaluators).

<a id="examination" style={{scrollMarginTop: "6rem"}} />

**examination** – a batch run that scores one or more models on a dataset using one or more evaluators, then reports aggregated statistics, per-row scores, and charts. A run is queued, then in progress, then completed or failed. See [Run examinations](/guard/app/examinations).

<a id="expected-output" style={{scrollMarginTop: "6rem"}} />

**expected output** – the reference or ground-truth answer for an input, which evaluators compare the model's output against, using methods such as exact match, BLEU, or ROUGE. When you upload a dataset, you map it to the **Assistant Message** template. See [Add and manage datasets](/guard/app/datasets).

[↑ Back to top](/guard/glossary)

## J

<a id="judge-model" style={{scrollMarginTop: "6rem"}} />

**judge model** – a model that scores a response rather than producing one. An LLM-as-a-Judge evaluator supplies the criteria and a judge model applies them. In an examination you choose judge models for each evaluator; in a comparison you choose them in **Judge Models**. See [Run comparisons](/guard/app/comparisons).

[↑ Back to top](/guard/glossary)

## L

<a id="llm-as-a-judge" style={{scrollMarginTop: "6rem"}} />

**LLM-as-a-Judge** – an evaluator you create that uses one or more other LLMs to score a model's output against your criteria. You pick those models when you add it to an examination. See [Create evaluators](/guard/app/evaluators).

[↑ Back to top](/guard/glossary)

## M

<a id="max-tokens" style={{scrollMarginTop: "6rem"}} />

**max tokens** – the maximum length, in tokens, of a model's response. On the Chat page, you can set it between 128 and 4096. See [Chat with a model](/guard/app/chat).

<a id="memory" style={{scrollMarginTop: "6rem"}} />

**memory** – on the Chat page, the **Use conversation history** toggle. When on, the model sees all previous messages in the conversation. When off, each message is independent. See [Chat with a model](/guard/app/chat).

<a id="method-risk-profile" style={{scrollMarginTop: "6rem"}} />

**method (risk profile)** – how a risk profile combines its category scores into an overall risk score: weighted linear, with penalties, or multiplicative. See [Build risk profiles](/guard/app/risk-profiles).

<a id="model" style={{scrollMarginTop: "6rem"}} />

**model** – a model you register in SeekrGuard from a provider, such as GPT-4 or Llama. Its type is foundational or fine-tuned, and its status is active, queued, or inactive. See [Register and manage models](/guard/app/models).

<a id="model-card" style={{scrollMarginTop: "6rem"}} />

**model card** – a model's profile page showing its details, a risk scorecard for a risk profile you select, and analysis tabs. See [Register and manage models](/guard/app/models).

[↑ Back to top](/guard/glossary)

## P

<a id="polarity" style={{scrollMarginTop: "6rem"}} />

**polarity** – a property of an evaluator's scoring scale that indicates which direction is better. Positive means higher scores are better outcomes; negative means higher scores are worse. When scores are combined into risk, negative-polarity ones are flipped so that higher always means more risk. See [Create evaluators](/guard/app/evaluators).

<a id="provider" style={{scrollMarginTop: "6rem"}} />

**provider** – the source of a model. When you register models you choose **OpenAI** or **Seekr**, which determines the models available to add. In the model list, the **Provider** column shows the organization each model came from, such as Google or Seekr. See [Register and manage models](/guard/app/models).

[↑ Back to top](/guard/glossary)

## R

<a id="risk-category" style={{scrollMarginTop: "6rem"}} />

**risk category** – a named risk dimension, such as factual accuracy, built by pairing one or more evaluators with the datasets they run against. Its aggregation method combines those scores into one category score, which a risk profile then weights. See [Build risk profiles](/guard/app/risk-profiles).

<a id="risk-level" style={{scrollMarginTop: "6rem"}} />

**risk level** – how a model's risk score is rated, from least to most risk: low, medium, high, or critical. In the **Model Risk Assessment** section of the Home page, it appears as a badge on each model's card and as a filter above them. See [Build risk profiles](/guard/app/risk-profiles).

<a id="risk-profile" style={{scrollMarginTop: "6rem"}} />

**risk profile** – a weighted set of risk categories for a particular use case, which produces an overall risk score and risk level for each model. A profile can be marked active, and the **Model Risk Assessment** section on the Home page scores models against an active profile you select. See [Build risk profiles](/guard/app/risk-profiles).

<a id="risk-score" style={{scrollMarginTop: "6rem"}} />

**risk score** – a model's overall risk under a risk profile, on a 0–100 scale where higher means more risk. It maps to a risk level and appears on each model's card in the **Model Risk Assessment** section of the Home page. See [Build risk profiles](/guard/app/risk-profiles).

<a id="rouge" style={{scrollMarginTop: "6rem"}} />

**ROUGE** – a metric that scores how much of the expected output a model's response covers. Higher scores mean more of the reference wording appears in the output. See [Create evaluators](/guard/app/evaluators).

<a id="rule-based-evaluator" style={{scrollMarginTop: "6rem"}} />

**rule-based evaluator** – an evaluator that applies fixed rules, such as pattern or constraint checks. Provided by SeekrGuard, with a **Default** badge under **Created By** in the evaluator library. See [Create evaluators](/guard/app/evaluators).

[↑ Back to top](/guard/glossary)

## S

<a id="sample-selection" style={{scrollMarginTop: "6rem"}} />

**sample selection** – the portion of a dataset an examination processes. When you create an examination, set it in the **Sample Selection** control as a percentage of the dataset or a number of samples; the control shows how many of the total samples will be used. See [Run examinations](/guard/app/examinations).

<a id="scoring-scale" style={{scrollMarginTop: "6rem"}} />

**scoring scale** – the range of scores an evaluator can produce, set by its **Minimum**, **Maximum**, and **Step**, along with its polarity. When you create an LLM-as-a-Judge evaluator, you define it in the configuration step. See [Create evaluators](/guard/app/evaluators).

<a id="statistical-evaluator" style={{scrollMarginTop: "6rem"}} />

**statistical evaluator** – an evaluator that computes a metric, such as ROUGE, BLEU, or exact match, usually against an expected output. Provided by SeekrGuard, with a **Default** badge under **Created By** in the evaluator library. See [Create evaluators](/guard/app/evaluators).

<a id="system-message" style={{scrollMarginTop: "6rem"}} />

**System Message** – the message template that holds a [system prompt](/guard/glossary#system-prompt).

<a id="system-prompt" style={{scrollMarginTop: "6rem"}} />

**system prompt** – an instruction that guides a model's behavior, such as *You are a helpful assistant.* When you upload a dataset, you map it to the **System Message** template. On the Chat page, **System Prompt** is one of the generation settings. See [Add and manage datasets](/guard/app/datasets) and [Chat with a model](/guard/app/chat).

[↑ Back to top](/guard/glossary)

## T

<a id="temperature" style={{scrollMarginTop: "6rem"}} />

**temperature** – a generation setting that controls randomness in a model's responses: lower is more deterministic, higher is more varied. On the Chat page, you can set it between 0 and 1. See [Chat with a model](/guard/app/chat).

[↑ Back to top](/guard/glossary)

## U

<a id="user-input" style={{scrollMarginTop: "6rem"}} />

**user input** – the user's question or query in a dataset input. When you upload a dataset, you map it to the **User Message** template. An evaluator that requires a user input can only run against datasets that supply one. See [Add and manage datasets](/guard/app/datasets).

<a id="user-message" style={{scrollMarginTop: "6rem"}} />

**User Message** – the message template that holds a [user input](/guard/glossary#user-input).

[↑ Back to top](/guard/glossary)

## V

<a id="visibility" style={{scrollMarginTop: "6rem"}} />

**visibility** – who can see and edit a resource:

* **Private** – only you.
* **Public (view only)** – everyone can see it, but no one else can edit it.
* **Public (collaborative)** – everyone can see it, and others can edit it.

See [Build risk profiles](/guard/app/risk-profiles).

[↑ Back to top](/guard/glossary)