Concept guide · LLMs and generative AI
When should an LLM refuse or ask a clarifying question?
A slower explanation for when the short interview answer is not enough. Start with the intuition, then connect it to the technical idea and the way an interviewer expects you to reason about it.
ML area
LLMs and generative AI → Advanced interview concept
Interview format
Advanced
Question
ML-110
Start with the idea
In simple terms
This question is asking you to explain When should an LLM refuse or ask a clarifying question in a way that connects the idea to a real machine-learning decision. Start with the role this concept plays, then explain what changes when the data, target, or deployment situation changes.
Build the answer
How to reason about it
- 1Define the concept before naming algorithms or implementation details.
- 2Connect it to the data, target, decision, or failure mode in the question.
- 3State the assumption or evaluation check that would make the explanation trustworthy.
Go one level deeper
The technical explanation
Refuse when the request violates a policy, exceeds the system's authority, or cannot be answered safely from the available evidence. Ask a clarifying question when multiple interpretations would lead to materially different answers or actions. Otherwise, answer with explicit assumptions and uncertainty. The policy should be enforced by application logic and tool permissions, not only by a natural-language instruction. The safest way to understand this topic is to connect the definition to assumptions, data available at prediction time, the decision it supports, and how you would evaluate whether the result is useful.
Say this in the interview
Refuse when the request violates a policy, exceeds the system's authority, or cannot be answered safely from the available evidence. Ask a clarifying question when multiple interpretations would lead to materially different answers or actions. Otherwise, answer with explicit assumptions and uncertainty. The policy should be enforced by application logic and tool permissions, not only by a natural-language instruction.
Keep preparing