LLM Limitations & Grounding
Recognize unsupported output and design evidence, citations, abstention, and evaluation.
Quick start
Reach one useful result first
- Explain
- 15 min
- Visualize
- 10 min
- Practice
- 25 min
- Deep dive
- 25 min
Explanation
Start with the direct answer, follow one example, then check your understanding.
Choose your explanation depth
The mechanism stays the same; emphasis and evidence change.
Fluent text can still be wrong because an LLM predicts language rather than verifying every claim.
Carried example
A policy assistant should answer from the supplied policy passage or say it lacks support instead of improvising.
Focus on the observable input, change, and output of grounding.
Learning goals and prerequisites
After this lesson
- Classify important LLM failure modes
- Map accepted claims to evidence
- Evaluate answerable, conflicting, and unanswerable cases
Helpful before starting
- LLM prompting
- Basic source and citation literacy
5 chapters · about 1 hr 3 min estimated study
0/5 chapters marked complete
Direct answer
Grounding gives a model identifiable evidence or verified tool results and accepts an answer only when its claims are supported by that evidence. When the required support is missing or conflicting, the system should clarify, answer partially, abstain, or escalate instead of filling the gap with plausible text.
Follow the mechanism
- Retrieve sources the user is authorized to access and preserve their identity, version, and freshness.
- Build a bounded context without separating passages from their provenance.
- Generate an answer whose claims cite the relevant source spans.
- Verify claim-to-evidence support and apply the configured abstention or escalation policy before release.
Running example
The available passage says: “Refunds are accepted within 30 days with a receipt.” For “How long do I have to request a refund?”, the answer “You can request a refund within 30 days if you have a receipt” is supported and can cite refund-policy. For “Is international shipping free?”, the same source provides no support. A fluent “yes” may sound helpful, but the correct grounded result is “I do not have evidence to answer that question.” The missing answer is a successful safety behavior, not an incomplete generation.
What this does not mean
Displaying a citation handle does not prove that the source supports the nearby claim. Retrieval can find the wrong passage, context construction can omit the right one, generation can contradict good evidence, and a validator can accept a citation that merely exists. Evaluate those stages separately so the correction targets the actual failure.
Ideas to understand
- Authorized retrieval → bounded context → cited claims → support verification → release policy is the grounding chain.
- A citation is useful only when the cited span supports the associated claim.
- Answerable, unanswerable, stale, and conflicting cases require separate evaluation fixtures.
- Abstention is correct output when the evidence contract cannot be satisfied.
Decision and failure guide
Use LLM Limitations & Grounding with evidence
A complete explanation includes the conditions that make the technique useful and the nearby ways it can fail.
Before you call it ready
- Preserve source identity
- Test missing and conflicting evidence
- Separate failure stages
- Escalate high-consequence uncertainty
Common failure → better decision
- Treating fluency as correctness
- Require support for accepted claims.
- Measuring answers without retrieval
- Evaluate pipeline stages separately.
- Citing a source that does not support the claim
- Check claim-to-span support.
Was this lesson helpful?
Submit to the team when server feedback is available; otherwise this browser keeps a local copy and tells you so.
Concept connections
See prerequisites, applications, and nearby decisions.
Learn before
Often compared with
Get one next lesson each week
A focused path reminder, not a marketing newsletter. Unsubscribe in one click.