Beam search is a decoding mechanism that looks back multiple time steps into the future rather than just one time step, keeping track of a fixed number of top-scoring tokens at each step and expanding them in a branch-and-bound fashion until the end of the sequence, producing better sentences than greedy single-token prediction.
factualpending
Speaker
Unidentified Speaker — 10 years of NLP history explained in 50 concepts | From Wor… [uocYQH0cWTs]Evidence Quote
“we employ a beam surge mechanism where the model looks back multiple time steps in the future instead of just one to find the most likely sequence of words by keeping track of a fixed number of top scoring tokens at each step and expanding them in a branch and bound like fashion”
Source
10 years of NLP history explained in 50 concepts | From Word2Vec, RNNs to GPT— Neural Breakdown with AVBCreated: 8/11/2026, 1:00:15 AM
Your notes
Loading notes...