LRanker: LLM Ranker for Massive Candidates

• URL: http://arxiv.org/abs/2605.27810v1
• Date: Wed, 27 May 2026 01:04:36 GMT
• Title: LRanker: LLM Ranker for Massive Candidates
• Abstract summary: We propose LRanker, a framework tailored for large-candidate ranking.<n>LRanker incorporates a candidate aggregation encoder that leverages K-means clustering to explicitly model global candidate information.<n>We evaluate LRanker on seven tasks across three scenarios in RBench with different candidate scales.
• Score: 32.698478901429375
• License: http://creativecommons.org/licenses/by/4.0/
• 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 framework 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 partitions 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.

Related papers

• LLM-as-a-Verifier: A General-Purpose Verification Framework [74.40111651545979]
  We introduce LLM-as-a-Verifier, a general-purpose verification framework.<n>It provides fine-grained feedback for agentic tasks without requiring additional training.<n>It achieves state-of-the-art performance on several benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:59:35Z)
• OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation [53.88666485159289]
  We introduce OpenDeepThink, a population-based test-time compute framework that selects via pairwise Bradley-Terry comparison.<n>OpenDeepThink raises Gemini 3.1 Pro's effective Codeforces Elo by +405 points in eight sequential LLM-call rounds.<n>We release CF-73, a curated set of 73 expert-rated Codeforces problems with International Grandmaster annotation and 99% local-evaluation agreement against the official verdict.
  arXiv  Detail & Related papers  (2026-05-14T17:57:40Z)
• F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking [79.49893545611779]
  Large Language Models (LLMs) can generate a subset and order it within a single autoregressive pass.<n>This flexibility introduces a new optimization challenge: the model must search an output space while receiving utility feedback only after the full ranked list is generated.<n>This credit assignment gap makes end-to-end optimization unstable and sample-inefficient.<n>We propose a unified framework that performs both within a single autoregressive rollout and optimize them end-to-end via factorized group-relative policy optimization.
  arXiv  Detail & Related papers  (2026-05-13T04:52:33Z)
• One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation [2.5827686695037335]
  Large language models (LLMs) are increasingly used for recommendation reranking, but their listwise predictions can depend on the order in which candidates are presented.<n>This creates a mismatch between the set-based nature of recommendation and the sequence-based computation of decoder-only LLMs.<n>We propose InvariRank, a permutation-invariant listwise reranking framework that addresses this dependence at the architectural level.
  arXiv  Detail & Related papers  (2026-04-30T08:49:44Z)
• Agentic AI for Human Resources: LLM-Driven Candidate Assessment [4.271562161453985]
  We present a modular and interpretable framework that uses Large Language Models (LLMs) to automate candidate assessment in recruitment.<n>The system integrates diverse sources, including job descriptions, CVs, interview transcripts, and HR feedback, to generate structured evaluation reports that mirror expert judgment.<n>The framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring.
  arXiv  Detail & Related papers  (2026-03-17T21:32:08Z)
• RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty [102.02839046225468]
  RankLLM is a novel framework designed to quantify both question difficulty and model competency.<n>We evaluate 30 models on 35,550 questions across multiple domains.
  arXiv  Detail & Related papers  (2026-02-12T21:28:46Z)
• GRAPE: Let GPRO Supervise Query Rewriting by Ranking for Retrieval [19.73916326078242]
  The CLIP model has become a cornerstone of large-scale retrieval systems by aligning text and image data in a unified embedding space.<n>To avoid costly retraining, existing methods mainly adopt query-rewriting strategies with large language models (LLMs)<n>We address this challenge with GRAPE, a plug-and-play enhancement approach that incorporates ranking signals into retrieval-guided query rewriting.
  arXiv  Detail & Related papers  (2025-09-27T15:36:59Z)
• R1-Ranker: Teaching LLM Rankers to Reason [35.35360001710222]
  R1-Ranker is a reasoning-incentive framework built on reinforcement learning.<n>IRanker decomposes ranking into an iterative elimination process with step-wise rewards to encourage deeper reasoning.<n>We evaluate unified R1-Rankers on nine datasets spanning recommendation, routing, and passage ranking.
  arXiv  Detail & Related papers  (2025-06-25T17:56:06Z)
• hyperFA*IR: A hypergeometric approach to fair rankings with finite candidate pool [0.0]
  We present hyperFA*IR, a framework for assessing and enforcing fairness in rankings drawn from a finite set of candidates.<n>It relies on a generative process based on the hypergeometric distribution, which models real-world scenarios by sampling without replacement from fixed group sizes.<n>We also propose a Monte Carlo-based algorithm that efficiently detects unfair rankings by avoiding computationally expensive parameter tuning.
  arXiv  Detail & Related papers  (2025-06-17T09:45:08Z)
• Self-Calibrated Listwise Reranking with Large Language Models [137.6557607279876]
  Large language models (LLMs) have been employed in reranking tasks through a sequence-to-sequence approach. This reranking paradigm requires a sliding window strategy to iteratively handle larger candidate sets. We propose a novel self-calibrated listwise reranking method, which aims to leverage LLMs to produce global relevance scores for ranking.
  arXiv  Detail & Related papers  (2024-11-07T10:31:31Z)
• Language Model Preference Evaluation with Multiple Weak Evaluators [89.90733463933431]
  We introduce PGED, a novel approach that leverages multiple model-based evaluators to construct preference graphs, and then ensembles and denoises these graphs for acyclic, non-contradictory evaluation results.<n>We demonstrate PGED's superiority in three applications: 1) model ranking for evaluation, 2) response selection for test-time scaling, and 3) data selection for model fine-tuning.
  arXiv  Detail & Related papers  (2024-10-14T01:57:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.