Indian Institute of Technology Madras
BS Degree Programme · Examination & Study Paper
Introduction to Natural Language Processing
Transformers & LLM fine-tuning
Official Paper
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.
- Scientific calculator allowed for all calculations.
- Official answer key is sealed at the end of this sheet.
- Q1MCQ3 Marks·Choose one option
A company wants to optimize an LLM for programming tasks. Which approach is the most efficient if they have limited labeled data?
- ATrain a new model from scratch using a large programming dataset.
- BFine-tune a transformer model with instruction tuning.
- CUse Few-shot prompting with an existing LLM.
- DApply a BERT-based model instead of transformers.
- Q2MSQ4 Marks·Choose all correct options
Which of the following statements correctly describe how BERT differs from GPT and standard transformer models?
- ABERT is a bidirectional model, while GPT is autoregressive.
- BBERT uses masked language modeling (MLM), while GPT uses causal language modeling (CLM).
- CStandard transformers use encoder-only architectures, whereas BERT and GPT both use decoder-only architectures.
- DBERT is trained for sentence embeddings, while GPT is trained for next-token prediction.
- Q3MSQ4 Marks·Choose all correct options
Which of the following statements is/are incorrect regarding Reinforcement Learning from Human Feedback (RLHF), Supervised Instruction Fine-Tuning, LoRA, and QLoRA?
- ARLHF helps improve model behavior by learning from human preference rankings.
- BLoRA (Low-Rank Adaptation) reduces the number of trainable parameters by using low-rank matrices.
- CSupervised Instruction Fine-Tuning involves reinforcement learning for generating human-like responses.
- DQLoRA applies quantization to reduce memory consumption during fine- tuning.