Four 6x6 attention mask grids (a)-(d) with colored cells, to be matched with attention variants

(A) (a) : Random Local Attention,\ (b) : Strided Local Attention,\ (c) : Sparse Block Attention,\ (d) : Local + Global Attention

(B) (a) : Strided Local Attention,\ (b) : Local + Global Attention,\ (c) : Random Local Attention,\ (d) : Sparse Block Attention

(C) (a) : Strided Local Attention,\ (b) : Random Local Attention,\ (c) : Local + Global Attention,\ (d) : Sparse Block Attention

(D) (a) : Sparse Block Attention,\ (b) : Local + Global Attention,\ (c) : Strided Local Attention,\ (d) : Random Local Attention

LLM End Term: 31 August 2025, Set QDB3 (May 2025 term)

Question 1

+3 marksOne correct option

Given the input string:

sunshine

And the following vocabulary of subword tokens with their corresponding log-probabilities:

Subword	Log-Probability (base $e$ )
`sun`	-0.5
`shine`	-0.7
`sunshine`	-1.6
`su`	-0.3
`nshine`	-0.4
`n`	-1.8
`shi`	-0.6
`ne`	-0.5

Using the Viterbi algorithm (as used in the SentencePiece tokenizer), determine the most probable tokenization of the input string. The probability of a tokenized sequence is the sum of the log-probabilities of the selected subwords. Only subwords from the vocabulary may be used.

Question 2

+2 marksOne correct option

A GPT model is trained using causal language modeling. During training, for a sequence of T = 4 tokens, which of the following correctly represents the attention mask matrix applied to the attention logits?

Question 3

+2 marksOne correct option

A
(a) : Random Local Attention,
(b) : Strided Local Attention,
(c) : Sparse Block Attention,
(d) : Local + Global Attention
B
(a) : Strided Local Attention,
(b) : Local + Global Attention,
(c) : Random Local Attention,
(d) : Sparse Block Attention
C
(a) : Strided Local Attention,
(b) : Random Local Attention,
(c) : Local + Global Attention,
(d) : Sparse Block Attention
D
(a) : Sparse Block Attention,
(b) : Local + Global Attention,
(c) : Strided Local Attention,
(d) : Random Local Attention

14 more questions in this paper

Sign in with Google — it is free — to see every question with its answer and explanation, practise it in learning mode, or take it as a timed mock test.

More on the LLM End Term 31 Aug 2025 Set QDB3 paper

The IIT Madras BS Large Language Models (LLM) End Term paper sat on 31 Aug 2025, in the May 2025 term, set QDB3: 17 questions for 40 marks in 180 minutes. The first 3 questions are below. Sign in with Google — it is free — to see the whole paper with its answers and explanations, in learning mode or as a timed mock test.

Feature	LLM End Term 31 Aug 2025 Set QDB3 at a glance
Term	May 2025 term
Subject	Large Language Models
Course code	BSDA5004
Questions	17
Marks	40
Duration	180 min
MCQ	6
MSQ	3
Numerical	8
Official paper	IIT M DEGREE AN EXAM QDB3 31 Aug 2025
Negative marking	No negative marking.
Updated	25 Sept 2026

Other sets that day

Set QDB1