Indian Institute of Technology Madras
BS Degree Programme · Examination & Study Paper
Introduction to Natural Language Processing
Retrieval-augmented generation
Examination Instructions & Guidelines
- Solve on notebook/paper first before checking solutions.
- MCQ: Exactly 1 option is correct. Negative marking applies.
- MSQ: One or more options correct. Select all to score.
- NAT: Numerical response. No negative marking.
- Scientific calculator allowed for all calculations.
- Official answer key is sealed at the end of this sheet.
- Q1MCQ3 Marks·Choose one option
How does Retrieval-Augmented Generation (RAG) differ from standard parametric models like GPT-3?
- ARAG eliminates the need for transformer-based token generation.
- BRAG uses retrieval but does not update its knowledge dynamically over time.
- CRAG only works when trained on labeled question-answer datasets.
- DRAG retrieves external documents dynamically, reducing reliance on pre- trained knowledge.
- Q2MCQ3 Marks·Choose one option
Which of the following architectures is most commonly used as the generator in RAG models?
- AGPT-3
- BBART
- CBERT
- DRoBERTa
- Q3MSQ4 Marks·Choose all correct options
Which components are essential in a RAG pipeline?
- Aretriever model (e.g., DPR) that fetches relevant documents.
- Bdecoder-only transformer for sequence generation.
- CBM25-based sparse retrieval method as the primary retriever.
- DBERT-based query encoder for document ranking.
- Q4NAT4 Marks·Write the number
A transformer-based Retrieval-Augmented Generation (RAG) system retrieves the top-10 most relevant passages, where each passage contains 512 tokens. However, a portion of the model's 4096-token context length is reserved for the input query and special tokens (e.g., separators, instructions). If the model reserves 1024 tokens for the input query, how many full retrieved passages can fit within the remaining context window?
Your answer: