Quiz Space

Deep Learning Practice · Quiz 1 · 26 Oct 2025 · September 2025 term

Question 11: The evolution of NLP models shows a distinct shift from …

Question 11

+4 marksOne or more correct options

The evolution of NLP models shows a distinct shift from task-specific architectures to a ”pre-train, finetune” paradigm, and now towards large-scale, general-purpose models. Which of the following accurately represents this evolution and the capabilities at each stage? (Select ALL that apply)

Select all that apply.

  1. A

    The earliest models (e.g., n-grams) were statistical, required task-specific design, and had limited generalization capacity.

  2. B

    The ”pre-train, fine-tune” era (e.g., BERT, GPT) introduced transfer learning, where a model was first trained on a general language task and then fully adapted to a specific downstream task.

  3. C

    Modern Large Language Models (LLMs like GPT-4) exhibit ”emerging abilities,” allowing them to perform new tasks with zero or few examples (in-context learning) without any weight updates.

  4. D

    Word2vec was a complete language model capable of generating text, similar to GPT.

  5. E

    The primary innovation of transformers over RNNs was the use of recurrent connections, which made them more efficient to train on parallel hardware.

Show answer

Correct answers

  • A

    The earliest models (e.g., n-grams) were statistical, required task-specific design, and had limited generalization capacity.

  • B

    The ”pre-train, fine-tune” era (e.g., BERT, GPT) introduced transfer learning, where a model was first trained on a general language task and then fully adapted to a specific downstream task.

  • C

    Modern Large Language Models (LLMs like GPT-4) exhibit ”emerging abilities,” allowing them to perform new tasks with zero or few examples (in-context learning) without any weight updates.

Question 11 of 15 in the IIT Madras BS Deep Learning Practice (Deep Learning Practice) Quiz 1 paper sat on 26 Oct 2025, in the September 2025 term (IIT M DEGREE AN EXAM QDB2 26 Oct 2025). It carries 4 marks.

More questions from this paper

  1. Q1Which of the following statements best describes the primary advantage of the SentencePiece tokenizer compared to a sta…
  2. Q2When performing full fine-tuning of a large language model (e.g., 10B parameters) using Adam, which component consumes …
  3. Q3A company wants to align its chatbot with values of being helpful, harmless, and honest. Human labelers provide ideal r…
  4. Q4Figure question
  5. Q5After running the following Hugging Face datasets code snippet, what will be the features of the dataset?
  6. Q6What is a key implication of using a Parameter-Efficient Fine-Tuning (PEFT) method like LoRA when adapting a large lang…
  7. Q7The WordPiece tokenization algorithm, unlike BPE, does not merge the pair with the highest frequency. Instead, it merge…
  8. Q8Which of the following statements accurately describes the Causal Language Modeling (CLM) objective used to pre-train m…
  9. Q9A research lab has access to a powerful 175B parameter language model. They need to adapt it for a highly specialized l…
  10. Q10A team is fine-tuning a 7B parameter model on a single GPU with 24GB of memory. They are using the Adam optimizer (whic…
  11. Q12The three main families of Transformer-based models are Encoder-only (e.g., BERT), Decoder-only (e.g.,GPT), and Encoder…
  12. Q13Figure question
  13. Q14A single transformer block in a GPT-style model has the following configuration: embedding dimension (d model) = 1024, …
  14. Q15You are given a GPT-style model with a vocabulary size of 50,257, a context length of 1024, and an embedding dimension …