Reduce LLM hallucination and handle class imbalance

Q: Reduce LLM hallucination and handle class imbalance

This question evaluates applied machine learning competencies including LLM safety and hallucination mitigation, retrieval-augmented generation and token-cost trade-offs, imbalanced classification handling, and precision-versus-recall decision-making within the Machine Learning domain for a Data Scientist role.

Q: How do I approach Machine Learning interview questions?

Machine Learning questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master machine learning interviews.

Question

Loading...

Answer the following applied ML/LLM questions.

1) LLM hallucination & token cost control

You are building a chatbot over an internal knowledge base.

What are common causes of hallucination in LLM chatbots?
How would you reduce hallucinations using a RAG-style approach (retrieval + generation)?
How would you control or reduce token costs while maintaining answer quality?

Discuss concrete design choices (e.g., chunking, retrieval quality, prompt construction), evaluation ideas, and failure modes.

2) Class imbalance + precision vs. recall trade-off

You are building a binary classifier where the positive class is rare.

How would you handle class imbalance during training and evaluation?
In a scenario where false positives are more costly than false negatives , which metric should be prioritized (precision vs. recall), and how would you choose an operating threshold?

Explain your reasoning and mention practical checks/pitfalls (e.g., calibration, dataset shift).

Reduce LLM hallucination and handle class imbalance

1) LLM hallucination & token cost control

2) Class imbalance + precision vs. recall trade-off

Solution

Comments (0)

Reduce LLM hallucination and handle class imbalance

Overview

1) LLM hallucination & token cost control

2) Class imbalance + precision vs. recall trade-off

Solution

Comments (0)