AI Knowledge Information 4

Question 1

In information theory, what does 'entropy' measure in the context of a knowledge source?

Accepted Answer

The average number of bits needed to encode information from a source

Answer

Shannon entropy quantifies the average uncertainty or information content of a random variable, measuring how many bits are needed on average to represent outcomes.

Question 2

Which technique is used to evaluate whether a language model's generated answer is faithful to a retrieved source document?

Accepted Answer

Faithfulness evaluation (e.g., using NLI models)

Answer

Faithfulness evaluation uses natural language inference (NLI) models or dedicated metrics to check whether generated claims are logically entailed by the source document.

Question 3

What is 'sparse retrieval' in the context of document search for AI systems?

Accepted Answer

Retrieving documents using term-frequency-based methods like BM25

Answer

Sparse retrieval relies on lexical matching using bag-of-words representations and algorithms like TF-IDF or BM25, contrasted with dense retrieval using neural embeddings.

Question 4

What challenge does 'knowledge staleness' pose for AI engineers deploying production systems?

Accepted Answer

The model's internal knowledge diverges from current real-world facts over time

Answer

Knowledge staleness means a deployed model's parametric knowledge becomes outdated as the world changes, requiring mitigation via RAG, fine-tuning updates, or knowledge editing.

Question 5

Which approach best mitigates conflicting information when merging multiple knowledge sources?

Accepted Answer

Apply source authority scoring and conflict resolution rules

Answer

Conflict resolution strategies assign trust scores to sources based on authority or provenance and apply rules (e.g., majority vote, recency weighting) to resolve contradictions.

AI - Engineer Practice Test

AI - Engineer Practice Test

AI Knowledge Information 4