LRanker: LLM Ranker for Massive Candidates

ICLR 2026 Conference Submission20091 Authors

Keywords: Large candidates, Ranking, Scalability, Large Language Models

TL;DR: LRanker is a scalable LLM-based ranking framework that uses aggregated centroids and test-time ensembles to handle ultra-large candidate sets efficiently.

Abstract:

Large language models (LLMs) have recently shown strong potential for ranking
by capturing semantic relevance and adapting across diverse domains, yet existing
methods remain constrained by limited context length and high computational
costs, restricting their applicability to real-world scenarios where candidate pools
often scale to millions. To address this challenge, we propose LRanker, a frame-
work tailored for large-candidate ranking. LRanker incorporates a candidate
aggregation encoder that leverages K-means clustering to explicitly model global
candidate information, and a graph-based test-time scaling mechanism that parti-
tions candidates into subsets, generates multiple query embeddings, and integrates
them through an ensemble procedure. By aggregating diverse embeddings instead
of relying on a single representation, this mechanism enhances robustness and
expressiveness, leading to more accurate ranking over massive candidate pools.
We evaluate LRanker on seven tasks across three scenarios in RBench with
different candidate scales. Experimental results show that LRanker achieves
over 30% gains in the RBench-Small scenario, improves by 3–9% in MRR in the
RBench-Large scenario, and sustains scalability with 20–30% improvements in the
RBench-Ultra scenario with more than 6.8M candidates. Ablation studies further
verify the effectiveness of its key components. Together, these findings demonstrate
the robustness, scalability, and effectiveness of LRanker for massive-candidate
ranking.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 20091