Context Steering in Foundry LLM Applications
HOTSPOT
You are building an app that will provide users with definitions of common AI terms.
You create the following Python code.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth point.
Community Insight
The question evaluates whether adding explicit contextual constraints (e.g., 'in the context of AI') effectively resolves ambiguity and improves response certainty, which is a key aspect of building reliable generative apps.
This scenario tests the implementation of context steering to ensure Large Language Models provide accurate definitions for ambiguous terms like 'LLM' in a specific domain.
Learners often assume that simply asking a question is sufficient for an LLM to infer the correct context, ignoring that without explicit steering, models may default to more common or general interpretations (like 'Master of Laws').
Community Discussion (1 comments)
Comments & Corrections
No comments yet — spotted an error or have a note? Share it below.
Expert Analysis
Why the Answer Is Correct
The core concept here is context steering, a technique used in Foundry to guide LLMs toward specific domains. The first statement claims that the original prompt ('What is an LLM?') yields high certainty; this is false because 'LLM' is ambiguous (Legal vs. Technical). The second statement suggests adding 'in the context of AI'; this is true because explicit context reduces ambiguity and aligns the model's probability distribution with the intended domain.Why Other Candidate Answers Are Wrong
There are no other candidate answers as this is a binary True/False evaluation of specific statements. However, a wrong approach would be to assume the LLM inherently understands the user's intent without guidance, or to believe that complex system prompts are needed instead of simple contextual phrasing.Community Comment Notes
As Amelia233 noted, the abbreviation 'LLM' is ambiguous and can mean Master of Laws in a legal context; without context steering, the model may return legal definition results instead of AI definitions. This highlights why the first statement is 'No' and the modified prompt is 'Yes'.Exam Strategy
When building generative apps, always consider if your input terms are ambiguous. If they are, use context steering by explicitly stating the domain (e.g., 'in the context of...') to improve output accuracy and reduce hallucinations.
Frequently Asked Questions
Why is 'LLM' considered ambiguous in the first prompt?
'LLM' commonly stands for both 'Large Language Model' in tech and 'Master of Laws' in legal education. Without context, the LLM cannot determine which definition the user wants.
How does context steering improve LLM responses?
Context steering adds explicit constraints to the prompt, guiding the model's attention mechanism to focus on relevant tokens and domain-specific knowledge, thereby reducing irrelevant outputs.
Related Analysis
Practice All AI-103 Questions
Access 88 questions with complete answers and detailed explanations.
View Full AI-103 Practice Test →