Using unselected top-k candidate tokens from a single LLM decoding pass as extra query terms improves retrieval over standard keyword expansion while using far fewer tokens than document-level methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Upcycling Candidate Tokens of Large Language Models for Query Expansion
Using unselected top-k candidate tokens from a single LLM decoding pass as extra query terms improves retrieval over standard keyword expansion while using far fewer tokens than document-level methods.