{
    "api": "YAML JSON TOON Database",
    "version": "1.0.0",
    "format": "json",
    "dataset": {
        "id": 5,
        "slug": "llm-glossary",
        "title": "Large Language Model Glossary",
        "description": "Key terms and concepts in LLM technology: tokens, context windows, temperature, RAG, fine-tuning, quantization, KV cache, and emergence.",
        "summary": "A glossary of large-language-model terms with precise definitions: tokens, context windows, temperature, retrieval-augmented generation, fine-tuning, quantization, KV cache and emergence, extended with embeddings, prompts, hallucination, sampling methods, RLHF, tool use, agents, mixture of experts, distillation, LoRA, perplexity and prompt injection.",
        "use_when": [
            "You need a one-sentence definition of an LLM term for documentation or a prompt.",
            "You are aligning a team on shared vocabulary."
        ],
        "caveats": [
            "The field changes fast; definitions here are conceptual and avoid claims about specific models.",
            "Some terms (agent, emergence) are used loosely and with different meanings across papers and products.",
            "Temperature zero does not guarantee reproducibility across hardware, serving systems, or model revisions."
        ],
        "related": [
            "attention-mechanisms",
            "transfer-learning",
            "ml-evaluation-metrics",
            "ai-ethics-interpretability",
            "llm-evaluation-failure-modes"
        ],
        "category": "AI & ML Terms",
        "category_slug": "ai-ml-terms",
        "tags": "llm,ai,glossary,nlp",
        "view_count": 0,
        "created_at": 1777673262,
        "updated_at": 1791799373,
        "sources": [
            {
                "title": "Stanford HELM evaluation framework",
                "url": "https://crfm.stanford.edu/helm/latest/"
            },
            {
                "title": "Hugging Face generation parameters",
                "url": "https://huggingface.co/docs/transformers/main/en/main_classes/text_generation"
            },
            {
                "title": "Schaeffer et al. on emergence and metric choice",
                "url": "https://arxiv.org/abs/2304.15004"
            }
        ],
        "reading": [
            "llm-evaluation-checklist-for-reference-grounded-answers"
        ],
        "reviewed_at": "2026-10-12",
        "provenance": "Original editorial reference notes by YJTOON, informed by the linked primary documentation. External specifications retain their own licenses.",
        "entry_count": 41,
        "fields": [
            {
                "section": "terms",
                "field": "term",
                "type": "string",
                "example": "Token"
            },
            {
                "section": "terms",
                "field": "definition",
                "type": "string",
                "example": "A unit of text processed by LLMs, typically a w…"
            }
        ]
    },
    "data": {
        "terms": [
            {
                "term": "Token",
                "definition": "A unit of text processed by LLMs, typically a word fragment or punctuation"
            },
            {
                "term": "Context Window",
                "definition": "Maximum number of tokens an LLM can process in a single inference"
            },
            {
                "term": "Temperature",
                "definition": "A parameter that rescales sampling logits; lower values concentrate probability. Zero-temperature behavior and reproducibility depend on the implementation."
            },
            {
                "term": "RAG",
                "definition": "Retrieval-Augmented Generation: combining LLMs with external knowledge retrieval"
            },
            {
                "term": "Fine-tuning",
                "definition": "Adapting a pre-trained model to specific tasks with additional training"
            },
            {
                "term": "Quantization",
                "definition": "Reducing model precision (e.g., FP16 to INT8) to decrease size and increase speed"
            },
            {
                "term": "KV Cache",
                "definition": "Key-Value cache storing attention computations for efficient autoregressive generation"
            },
            {
                "term": "Emergence",
                "definition": "A capability whose measured performance appears to change sharply with scale; the appearance can depend on the metric and evaluation design."
            },
            {
                "term": "Embedding",
                "definition": "A dense vector representing text or another input so that semantically similar items are close in vector space"
            },
            {
                "term": "Prompt",
                "definition": "The input text, including instructions and examples, given to a model to elicit a response"
            },
            {
                "term": "System Prompt",
                "definition": "Instructions set by the application developer that frame the model's role and behavior for a conversation"
            },
            {
                "term": "Hallucination",
                "definition": "Output that is fluent and confident but false or unsupported by the provided sources"
            },
            {
                "term": "Top-p (Nucleus Sampling)",
                "definition": "Sampling from the smallest set of tokens whose cumulative probability exceeds p, which adapts the candidate set to the distribution"
            },
            {
                "term": "Top-k Sampling",
                "definition": "Sampling from only the k most probable next tokens"
            },
            {
                "term": "Inference",
                "definition": "Running a trained model to produce outputs, as opposed to training it"
            },
            {
                "term": "Pretraining",
                "definition": "The initial large-scale training of a model on broad data to learn general patterns before specialization"
            },
            {
                "term": "Instruction Tuning",
                "definition": "Fine-tuning a model on examples of instructions and desired responses so it follows directions"
            },
            {
                "term": "RLHF",
                "definition": "Reinforcement learning from human feedback: tuning a model using human preference judgments as a reward signal"
            },
            {
                "term": "Chain-of-Thought",
                "definition": "Prompting or training a model to produce intermediate reasoning steps before a final answer"
            },
            {
                "term": "Few-Shot Prompting",
                "definition": "Including a handful of worked examples in the prompt to show the desired task format"
            },
            {
                "term": "Zero-Shot",
                "definition": "Performing a task from instructions alone, with no examples in the prompt"
            },
            {
                "term": "In-Context Learning",
                "definition": "A model's ability to adapt to a task from examples or instructions in the prompt without updating its weights"
            },
            {
                "term": "Tool Use (Function Calling)",
                "definition": "A model emitting structured calls to external functions or APIs, whose results are returned to it"
            },
            {
                "term": "Agent",
                "definition": "A system in which a model repeatedly decides on actions, uses tools and observes results to pursue a goal"
            },
            {
                "term": "Mixture of Experts",
                "definition": "An architecture that routes each token to a few specialized sub-networks, increasing capacity without activating all parameters"
            },
            {
                "term": "Distillation",
                "definition": "Training a smaller model to imitate the outputs of a larger one"
            },
            {
                "term": "LoRA",
                "definition": "Low-rank adaptation: fine-tuning by training small added matrices while keeping the base weights frozen"
            },
            {
                "term": "Perplexity",
                "definition": "A measure of how well a language model predicts text; lower means the text is less surprising to the model"
            },
            {
                "term": "Prompt Injection",
                "definition": "An attack that places instructions in untrusted input so the model follows them in place of the developer's"
            },
            {
                "term": "Guardrails",
                "definition": "Checks and constraints around a model that filter inputs and outputs to keep behavior within policy"
            },
            {
                "term": "Multimodal",
                "definition": "Able to process more than one kind of input or output, such as text, images and audio"
            },
            {
                "term": "Vector Database",
                "definition": "A store optimized for nearest-neighbor search over embeddings"
            },
            {
                "term": "Chunking",
                "definition": "Splitting documents into pieces of suitable size for embedding and retrieval"
            },
            {
                "term": "Logits",
                "definition": "The raw, unnormalized scores a model produces for each possible next token before softmax"
            },
            {
                "term": "Alignment",
                "definition": "The effort to make model behavior match human intentions and values"
            },
            {
                "term": "Scaling Laws",
                "definition": "Empirical relationships showing how model loss improves predictably with more parameters, data and compute"
            },
            {
                "term": "Model Context Protocol (MCP)",
                "definition": "An open protocol that standardizes how applications give models access to tools and data sources"
            },
            {
                "term": "Groundedness",
                "definition": "Whether answer claims are supported by the supplied evidence; it differs from whether the evidence itself is correct."
            },
            {
                "term": "Calibration",
                "definition": "Agreement between stated or estimated confidence and observed correctness over a set of predictions."
            },
            {
                "term": "Held-out Evaluation",
                "definition": "Assessment on cases withheld from development choices, to reduce optimistic bias from repeated tuning."
            },
            {
                "term": "Abstention",
                "definition": "Declining to answer when the evidence or confidence is insufficient, according to an explicit policy."
            }
        ]
    }
}