Jev glossary
PatternsBeam search
Parallel beam search
Keep the top-k branches at each taxonomy level instead of only the winner, so a wrong first choice can still be recovered.
- Category
- Patterns
- Also known as
- Beam search
- Reading time
- 1 min
- Related terms
- 3
- Directory entries
- 1
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Beam search over Choice probabilities asks one question per surviving node at each level and keeps the best few paths, pruning the rest. It uses the probability distribution the answer already returns as the ranking signal.
It is the mitigation for greedy hierarchical classification: committing to the single top choice at level one turns a 0.7 into a hard decision, while a beam keeps a runner-up alive until the evidence separates.
Tagspatternsclassification
Related terms
Definitions that connect to this one.
Hierarchical classificationWalk a deep taxonomy level by level, using each Choice answer to pick the next level's options, keeping several paths alive.PatternsProbability distributionThe floats summing to 1 across your options or levels that every Choice and Score answer returns under probabilities.Answers & ConfidenceRe-rankingScore each query-candidate pair with one question and reorder a shortlist; the CLERC example lifts top-1 accuracy from 5% to 18%.Patterns
From the Jev directory
Directory entries that go deeper on this term.
Classify documents through deep patent, retail product, biomedical, and source-code hierarchies using parallel beam search over Choice probabilities.
Jev CookbooksDocs#official#cookbook#classification
Official
From the Jev AI model community
Posts from builders shipping with Jev right now.