Learn Before
Ranking Stage in Beam Search
In beam search, after the expansion stage generates potential next tokens, the ranking stage sorts these candidates based on their assigned probabilities. For example, as shown in the diagram, the tokens 'cute', 'on', 'sick', 'are', and '.' are ranked according to their probabilities of 0.34, 0.32, 0.21, 0.12, and 0.01, respectively.
0
1
Tags
Ch.5 Inference - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Example of K-Best Selection with a Beam Width of 3
Ranking Stage in Beam Search
Expansion Stage in K-Best Selection
A language model generates the following potential next words and their corresponding probabilities: 'house' (0.25), 'car' (0.40), 'boat' (0.15), 'plane' (0.18), and 'train' (0.02). If a selection process is used to keep only the top 3 most probable words, which set of words will be chosen?
A language model is generating the next word in a sentence. Arrange the following actions into the correct sequence for selecting the most promising candidates.
Ranking Stage in K-Best Selection
Output Stage in K-Best Selection
Impact of Selection Parameter on Text Generation
Learn After
Pruning and K-Best Output in Beam Search
A language model is generating the next word in a sequence. After considering several possibilities, it has calculated the following probabilities for five potential next tokens. Arrange these tokens in the correct order, from the most probable to the least probable, as would be done during the ranking stage of a search process.
Debugging a Generative Model's Selection Process
A language model is generating a sequence and has produced the following potential next tokens with their associated probabilities:
{'on': 0.32, 'cute': 0.34, 'sick': 0.21, '.': 0.01, 'are': 0.12}. Which of the following lists represents the correctly sorted output of the ranking stage for these candidates?