PaPoo
日本語 / English
cover
aiterms
Author
aiterms
#llm-fundamentals#ai-glossary

What is grounding?

Grounding is the practice of connecting an AI model’s output to a real source of truth, so its answer is based on evidence instead of only pattern-matched text.

Why it matters

Large language models can sound confident even when they are wrong. Grounding helps reduce that by tying responses to something verifiable: a document, database, tool result, sensor reading, or other external source.

You reach for grounding when correctness matters more than fluency—customer support, enterprise search, policy answers, product documentation, data-heavy assistants, and any workflow where you want the model to cite or reflect known facts rather than improvise.

In practice, teams often use grounding before they try more advanced agent behavior. It is one of the simplest ways to make an assistant more trustworthy.

How it works

A grounded system usually does three things:

  1. Fetch relevant evidence.
    The app retrieves source material such as retrieved documents, database rows, or tool outputs.

  2. Constrain the model to that evidence.
    The prompt or system design tells the model to answer using only the provided sources, often with citations or quotes.

  3. Check the result.
    The application may verify that the answer references the retrieved content, reject unsupported claims, or ask for a fallback like “I don’t know.”

Grounding is not the same as making a model “smart.” It is a control technique: it narrows what the model should rely on. In retrieval-augmented generation (RAG), grounding is often the goal; retrieval is one way to achieve it.

Tiny concrete example

User asks:

“What is our refund window?”

The app retrieves the company policy:

“Customers may request a refund within 30 days of purchase.”

The model answers:

“Our refund window is 30 days from purchase.”

If the policy document is missing or unclear, a grounded assistant should say so instead of guessing:

“I couldn’t find the refund window in the sources I have.”

Common pitfalls / when NOT to use it

In short: use grounding when you need answers anchored to evidence, not when you need the model to invent, extrapolate, or compose freely.

Related terms

X に投稿 BlueSky に投稿
同じ著者の記事
What is LLM-as-a-judge?
What is LLM-as-a-judge?
LLM-as-a-judge is the practice of using a large language model to evaluate or rank outputs from another model, system, or workflow, instead of relying only on human reviewers or fixed metrics. It solves a common problem: many AI outputs are hard to score with simple automated checks. If you are judging a summary for usefulness, a chatbot answer for helpfulness, or two candidate responses for preference, exact-match metrics often miss the point. Teams reach for LLM-as-a-judge when they need: **Fa
papoo.work
What is an LLM eval (evaluation)?
What is an LLM eval (evaluation)?
An LLM eval, or evaluation, is a test or set of tests used to measure how well a large language model behaves on a task or under a specific set of conditions. If you build with LLMs, you need a way to answer practical questions like: Does this prompt change improve answer quality? Is the model following instructions more reliably? Did a new model version get worse on safety, latency, or factuality? An eval gives you a repeatable way to compare models, prompts, retrieval setups, or fine-tunes. In
papoo.work
What is a hallucination?
What is a hallucination?
A hallucination is when an AI system generates output that sounds plausible but is wrong, unsupported, or made up. Hallucinations matter because they break trust. If you use a model for search, summarization, coding help, or customer support, a confident but false answer can mislead users, create bugs, or spread bad information. In practice, teams care about hallucinations whenever they need factual accuracy, source grounding, or reliable behavior. For creative writing, they may be less of a pro
papoo.work
What is the KV cache?
What is the KV cache?
The KV cache, or key-value cache, is a memory buffer that stores past attention keys and values so a transformer can generate the next token without recomputing everything from scratch. In autoregressive generation, each new token depends on all previous tokens. Without a KV cache, the model would repeatedly re-run attention over the entire prefix at every step, which is much slower than necessary. You reach for a KV cache when you want faster text generation, lower latency, or higher throughput
papoo.work
What is a parameter (model size)?
What is a parameter (model size)?
A parameter is a learned number inside a model, and “model size” usually means how many of those learned numbers the model has. Parameters are the part of a neural network that gets updated during training, so they determine how much capacity the model has to fit patterns in data. You’ll care about parameter count when you want to compare models, estimate training cost, understand memory use, or get a rough sense of how much hardware a model needs. In practice, “bigger” often means more capable,
papoo.work
What is a mixture-of-experts (MoE) model?
What is a mixture-of-experts (MoE) model?
A mixture-of-experts (MoE) model is a neural network that routes each input, or part of an input, to only a small subset of specialized submodels (“experts”) instead of using the whole model every time. MoE models are useful when you want much larger capacity without paying the full compute cost on every token or example. In practice, that means you can scale model size to improve quality while keeping inference and training more efficient than a dense model of similar total parameter count.
papoo.work
What is a token (and tokenization)?
What is a token (and tokenization)?
A token is a chunk of text that a language model reads and predicts, and tokenization is the process of splitting text into those chunks. LLMs do not operate directly on raw characters or words; they operate on tokens. That matters because: Input limits are measured in tokens, not characters. Cost and latency are often tied to token count in LLM APIs. Model quality depends on how text is tokenized: the same sentence can become very different token sequences across tokenizers.
papoo.work
What is a transformer?
What is a transformer?
A transformer is a neural network architecture that processes sequences by using attention to compare each token with the others, making it a flexible foundation for modern language models and many other sequence tasks. Before transformers, many sequence models had to read text step by step, which made long-range dependencies harder to handle and training slower to parallelize. Transformers solve this by letting the model look at many positions in the input at once. In practice, you reach for a
papoo.work
What is attention (self-attention)?
What is attention (self-attention)?
Attention, or self-attention, is a way for a model to decide which other words or tokens in the same input matter most when interpreting each token. Self-attention solves a basic language problem: the meaning of a word often depends on other words nearby or far away. It lets a model build a context-aware representation of each token instead of treating tokens mostly independently or relying only on fixed-size windows. In practice, this is why Transformers work so well for text, code, and other s
papoo.work
What is temperature in an LLM?
What is temperature in an LLM?
Temperature is a sampling setting that controls how random or deterministic an LLM’s next-word choices are when it generates text. Temperature is one of the simplest ways to trade off consistency versus variety. Use a lower temperature when you want stable, repeatable answers: classification-like outputs, structured data, summaries, or code. Use a higher temperature when you want more diversity: brainstorming, creative writing, alternate phrasings, or exploratory chat. In practice, many
papoo.work