Hypothesis in LLM Inference

Mathematical Formulation of the Search Problem in LLM Inference

Exploration vs. Exploitation in LLM Search

Search Tree Structure in Token Generation

Heuristic Search Algorithms for LLM Inference

Efficient Generation of Candidate Solutions via Search Algorithms

Search for Optimal or Sub-optimal Sequences in LLM Inference

Root of the Search Space as a Representation of Input (x)

A text generation model has a vocabulary of 10,000 possible words it can choose from for each position in a sequence. If this model were to find the optimal output by evaluating every single possible sequence, how would the total number of sequences to check change if the desired output length is increased from 3 words to 5 words?

Evaluating an Inference Strategy

The Impracticality of Exhaustive Search

Historical Context and Computational Challenges of Maximum Probability Prediction

Mathematical Representation of an Output Sequence

Formula for the Search Space as a Union of Complete Sequences

Formula for the Expansion of the Search Space at Each Step

A simplified language model has a vocabulary consisting of only three unique tokens: 'cat', 'sat', and 'on'. The model is configured to generate an output sequence with a fixed length of exactly two tokens. Which of the following options correctly represents the complete set of all possible output sequences the model can generate?

Analyzing Search Space Dimensions

Growth of the Generative Search Space

Mathematical Formulation of the Search Problem in LLM Inference