Score: 1

Upcycling Candidate Tokens of Large Language Models for Query Expansion

Published: September 2, 2025 | arXiv ID: 2509.02377v1

By: Jinseok Kim , Sukmin Cho , Soyeong Jeong and more

Potential Business Impact:

Finds better search results with less computer power.

Business Areas:
Semantic Search Internet Services

Query Expansion (QE) improves retrieval performance by enriching queries with related terms. Recently, Large Language Models (LLMs) have been used for QE, but existing methods face a trade-off: generating diverse terms boosts performance but increases computational cost. To address this challenge, we propose Candidate Token Query Expansion (CTQE), which extracts diverse and relevant terms from a single LLM decoding pass by leveraging unselected candidate tokens. These tokens, though not part of the final output, are conditioned on the full query and capture useful information. By aggregating them, CTQE achieves both relevance and diversity without extra inference, reducing overhead and latency. Experiments show that CTQE delivers strong retrieval performance with significantly lower cost, outperforming or comparable to more expensive methods. Code is available at: https://github.com/bluejeans8/CTQE

Country of Origin
🇰🇷 Korea, Republic of

Repos / Data Links

Page Count
6 pages

Category
Computer Science:
Information Retrieval