AI Glossary Models and how they work

Grounding

  • Tidio Agents team
  • Updated November 19, 2026
  • 5 min read
  • 6 sources
Definition

Grounding in AI is the practice of tying a model's output to verifiable sources of information, such as documents, databases, or live system data, so that each claim in an answer is supported by a source and can be checked. A grounded answer says only what its sources support, and can point to them.

Google's documentation puts it simply: grounding is "the ability to connect model output to verifiable sources of information."1 A language model on its own writes what is statistically likely. Grounding changes the question it answers from "what usually comes next?" to "what do these sources say?"

The word has other meanings. In electrical work it means a connection to earth, in linguistics it is the shared understanding two speakers build, and in cognitive science the "symbol grounding problem" asks how symbols get meaning at all.5 This page covers the generative AI sense only.

How it works

Three parts of a grounded answer

Grounding is a property of an answer, and a system gets there in three moves: give the model the right sources, constrain it to them, and check the result.

SourcesAnswerCheckCiteunsupported claim: revisesend or hand overdocuments · order records · APIs · search
A grounded answer passes a check against its sources before it reaches the customer.

Sources in context

The model receives the evidence with the question: help-center passages through retrieval, an order record through a tool call, or search results.

Constraint

The instructions tell the model to answer only from that evidence and to say when it falls short. Without this, models mix sources with memory.

Verification

A separate check compares each claim with the sources. Microsoft's groundedness detection, for example, flags "ungrounded" text that departs from the source material.4

Citation

The answer links to the passages it used. Research benchmarks now score citation quality, and found that even strong models often lack full citation support.3

Example

Grounded and ungrounded, side by side

A customer of a bank's consumer lending arm asks about an installment plan. Both lanes use the same model and see the same customer record. One answer stays within it; the other does not.

Ungrounded

Fills gaps
CustomerIf I pay off my installment plan early, do I get the interest back?
  1. ContextSees the customer's plan: 12 installments, 4 paid. No document on early repayment was retrieved.
  2. Reply"Yes, early repayment is free and the remaining interest is refunded in full within 5 working days."

Confident, unsupported. Nothing in the context mentions refunds or timing. A customer may act on a promise the bank never made.

Grounded

Cites
CustomerIf I pay off my installment plan early, do I get the interest back?
  1. Toolloans.get(plan_id)→ 12 installments · 4 paid · agreement v3
  2. Retrievedocs.search("early repayment", agreement="v3")→ agreement v3 §7 · early repayment FAQ
  3. AnswerStates what §7 says about reducing the cost of credit, quotes the clause, and links the FAQ.
  4. CheckEvery claim matches a source. The amount is left to the repayment calculator, which the answer links.

Supported and checkable. The customer and the compliance team can both see where each sentence came from.

Illustrative example. Plan details, clause numbers, and tool names are placeholders.

Compared

Grounding, RAG, and hallucination

These terms describe a goal, a method, and a failure. They are easy to mix up.

TermWhat it isQuestion it answers
GroundingA property of an answer: every claim is backed by a sourceCan each sentence be traced to evidence?
Retrieval-augmented generationA method: fetch sources, then generate from them6How do the sources get into the prompt?
AI hallucinationA failure: content that is false or unsupportedWhat happens when grounding breaks?
Factual accuracyAgreement with the real worldIs it true, regardless of the sources?
Fine-tuningChanging the model's weightsHow does the model behave by default?

An answer can be grounded and still wrong, if the source itself is outdated. Grounding moves the quality problem to the sources, where a company can fix it.

In practice

Where grounding matters most

Grounding matters most where a wrong answer creates a commitment, a cost, or a compliance problem.

Customer support

Policy and contract answers

A telecom's agent answers contract and cancellation questions only from the customer's current plan terms, and cites them.

plan terms → answer → cite
Shopping

Specs from the catalog

A retailer's shopping agent states dimensions, compatibility, and stock only from catalog data, never from what similar products usually offer.

catalog → compare → recommend
Travel

Fare rules and changes

A travel company's agent explains change fees from the fare rules attached to the booking, not from general airline practice.

booking → fare rules → quote fee
Internal knowledge

Answers staff can trust

An insurer's claims handlers get procedure answers with the manual section linked, so they can check before acting.

question → manual → answer + link
Measure

How to measure groundedness

Groundedness can be scored, which makes it one of the more practical quality metrics for an agent.

Groundedness rate
supported claims ÷ all factual claims in sampled answers
Answers sampled
200
Factual claims found
640
Claims supported by a cited source
608
Groundedness rate
95%

Illustrative numbers, not a benchmark. Set your own target per use case.

  • Human review: annotators judge whether each statement is attributable to its source.2
  • Automated checks: a model or classifier compares claims with sources at scale, with people auditing a sample.4
  • Citation quality: whether the cited passage actually supports the sentence it is attached to.3
FAQ

Common questions

What does grounding mean in generative AI?

It means connecting a model's answer to verifiable sources, such as documents or system data, so each claim is supported and can be checked. A grounded answer says only what its sources support.

Is grounding the same as RAG?

No. Grounding is the goal, and retrieval-augmented generation is one method to reach it. A system can also ground answers in tool results, such as an order record, or in search results.

Does grounding eliminate hallucinations?

It reduces them and makes the rest easier to catch, because claims can be checked against sources. A model can still misread a source, and a grounded answer is only as accurate as the source it uses.

How do you know if an answer is grounded?

Split it into factual claims and check whether a cited source supports each one. Teams do this with human review on a sample and with automated groundedness checks on every answer.

Sources

References

  1. Google Cloud. Grounding overview. Official documentation.
  2. Rashkin, H. et al. Measuring Attribution in Natural Language Generation Models. arXiv, 2021.
  3. Gao, T. et al. Enabling Large Language Models to Generate Text with Citations. EMNLP 2023.
  4. Microsoft. Groundedness detection in Azure AI Content Safety. Official documentation.
  5. Harnad, S. The Symbol Grounding Problem. Physica D 42 (1990): 335-346.
  6. Lewis, P. et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. NeurIPS 2020.

Tidio Agents

Build an agent that resolves, not only answers

We design and build custom AI agents for customer service, shopping and back-office work, on your infrastructure, with the code handed over to you. Projects start with a 21-day private AI audit.

Request a call