Decoding Strategies & Prompt Engineering
← Question BankSign in to bookmark Sign in to bookmark Sign in to bookmark Sign in to bookmark Sign in to bookmark Sign in to bookmark Sign in to bookmark Sign in to bookmark Sign in to bookmark Sign in to bookmark Sign in to bookmark
Deep Learning & Generative AI
Generative AI & Large Language Models (LLMs) Interview Questions
Interview questions on Generative AI & Large Language Models (LLMs) Interview Questions.
12 questions
All subtopicsLLM Architectures & FoundationsTokenization & EmbeddingsAttention, KV Cache & Efficient InferenceLLM Training & Pre-trainingDecoding Strategies & Prompt EngineeringFine-Tuning & Model AdaptationRAG & Vector DatabasesAlignment & Preference OptimizationLLM Evaluation & BenchmarkingAgents, Tool Use & MemoryMultimodal Generative AILLM Safety & SecurityLLMOps & Production
Sign in to bookmark
Decoding Strategies & Prompt Engineering
Q2. What role does temperature play in controlling LLM output?
Decoding Strategies & Prompt Engineering
Q3. How do top-k and top-p sampling differ in text generation?
Decoding Strategies & Prompt Engineering
Q4. Explain the decoding strategies used in LLMs?
Decoding Strategies & Prompt Engineering
Q5. Can we use generative models for classification tasks? If so, how?
Decoding Strategies & Prompt Engineering
Q6. Why is prompt engineering crucial for LLM performance?
Decoding Strategies & Prompt Engineering
Q7. What are some good prompting techniques one should know?
Decoding Strategies & Prompt Engineering
Q8. What is Chain-of-Thought (CoT) prompting, and how does it aid reasoning?
Decoding Strategies & Prompt Engineering
Q9. What is self-consistency in prompting, and how does it help improve the quality of generative model outputs? What are its trade-offs?
Decoding Strategies & Prompt Engineering
Q10. What is zero-shot learning, and how do LLMs implement it?
Decoding Strategies & Prompt Engineering
Q11. What is few-shot learning, and what are its benefits?
Decoding Strategies & Prompt Engineering