# ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking

arXiv: https://arxiv.org/abs/2506.03487 · HTML: https://mlsanity.com/paper/2506.03487/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 12 of 12)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [CoIR: A Comprehensive Benchmark for Code Information Retrieval Models](https://mlsanity.com/paper/2407.02883/) (2024)
- [Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning](https://mlsanity.com/paper/2503.06034/) (2025)
- [Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking](https://mlsanity.com/paper/2310.13243/) (2023)
- [BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings](https://mlsanity.com/paper/2311.05296/) (2023)
- [Drowning in Documents: Consequences of Scaling Reranker Inference](https://mlsanity.com/paper/2411.11767/) (2024)

## Built on by (most cited first, 11 of 11)

- [Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use](https://mlsanity.com/paper/2604.05432/) (2026)
- [DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search](https://mlsanity.com/paper/2607.27178/) (2026)
- [TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking](https://mlsanity.com/paper/2508.09539/) (2025)
- [AgentSearchBench: A Benchmark for AI Agent Search in the Wild](https://mlsanity.com/paper/2604.22436/) (2026)
- [FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.14227/) (2026)
- [Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking](https://mlsanity.com/paper/2606.22807/) (2026)
- [Tool-Adaptive LLM Reranker](https://mlsanity.com/paper/2607.10555/) (2026)
- [Search over the Visual World: Persistent Visual Memory, Layered Indexes, and Source-Grounded Evidence](https://mlsanity.com/paper/2608.08075/) (2026)
- [Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers](https://mlsanity.com/paper/2608.26762/) (2026)
- [CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.04647/) (2026)
- [Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers](https://mlsanity.com/paper/2609.13486/) (2026)

## Abstract (arXiv)

Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most current works rely on large-scale LLMs (>7B parameters), presenting high computational costs. Small Language Models (SLMs) offer a promising alternative because of computational efficiency. However, our preliminary quantitative analysis reveals key limitations of SLMs: their representation space is narrow, leading to reduced expressiveness, and they struggle with understanding task prompts without fine-tuning. To address these issues, we introduce a novel two-stage training approach, ProRank, for SLM-based document reranking. We propose using reinforcement learning to improve the understanding of task prompts. Additionally, we introduce fine-grained score learning to enhance representation expressiveness and further improve document reranking quality. Extensive experiments suggest that ProRank consistently outperforms both the most advanced open-source and proprietary reranking models. Notably, our 0.5B ProRank even surpasses powerful LLM reranking models on the BEIR benchmark, establishing that properly trained SLMs can achieve superior document reranking performance while maintaining computational efficiency.