# ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking

arXiv: https://arxiv.org/abs/2509.00520 · HTML: https://mlsanity.com/paper/2509.00520/

## Key facts

- Cited by 6 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 22 of its 35 references that are in the map.
- First posted on arXiv 30 Aug 2025.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)
- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 22 of 22)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [ReasonIR: Training Retrievers for Reasoning Tasks](https://mlsanity.com/paper/2504.20595/) (2025)
- [Retrieval-Augmented Generation for Natural Language Processing: A Survey](https://mlsanity.com/paper/2407.13193/) (2024)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions](https://mlsanity.com/paper/2403.15246/) (2024)
- [Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline](https://mlsanity.com/paper/2101.08751/) (2021)
- [LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations](https://mlsanity.com/paper/2406.12433/) (2024)
- [Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models](https://mlsanity.com/paper/2409.11136/) (2024)
- [JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking](https://mlsanity.com/paper/2411.00142/) (2024)
- [Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering](https://mlsanity.com/paper/1810.00494/) (2018)
- [HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking](https://mlsanity.com/paper/2205.10569/) (2022)
- [A Two-Stage Adaptation of Large Language Models for Text Ranking](https://mlsanity.com/paper/2311.16720/) (2023)
- [Empirical Evaluation of ChatGPT on Requirements Information Retrieval Under Zero-Shot Setting](https://mlsanity.com/paper/2304.12562/) (2023)
- [ListConRanker: A Contrastive Text Reranker with Listwise Encoding](https://mlsanity.com/paper/2501.07111/) (2025)

## Built on by (most cited first, 6 of 6)

- [jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking](https://mlsanity.com/paper/2509.25085/) (2025)
- [E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search](https://mlsanity.com/paper/2510.22733/) (2025)
- [GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs](https://mlsanity.com/paper/2511.11653/) (2025)
- [A Survey of Reasoning-Intensive Retrieval: Progress and Challenges](https://mlsanity.com/paper/2605.00063/) (2026)
- [Question's Gambit: The First Move Matters in Agentic Deep Search](https://mlsanity.com/paper/2609.14412/) (2026)
- [Component-Aware Feedback for Self-Evolving Programs](https://mlsanity.com/paper/2609.38639/) (2026)

## Abstract (arXiv)

Text reranking models are a crucial component in modern systems like Retrieval-Augmented Generation, tasked with selecting the most relevant documents prior to generation. However, current Large Language Models (LLMs) powered rerankers often face a fundamental trade-off. On one hand, Supervised Fine-Tuning based pointwise methods that frame relevance as a binary classification task lack the necessary scoring discrimination, particularly for those built on reasoning LLMs. On the other hand, approaches designed for complex reasoning often employ powerful yet inefficient listwise formulations, rendering them impractical for low latency applications. To resolve this dilemma, we introduce ERank, a highly effective and efficient pointwise reranker built from a reasoning LLM that excels across diverse relevance scenarios. We propose a novel two-stage training pipeline that begins with Supervised Fine-Tuning (SFT). In this stage, we move beyond binary labels and train the model generatively to output fine grained integer scores, which significantly enhances relevance discrimination. The model is then further refined using Reinforcement Learning (RL) with a novel, listwise derived reward. This technique instills global ranking awareness into the efficient pointwise architecture. We evaluate the ERank reranker on the BRIGHT, FollowIR, TREC DL, and BEIR benchmarks, demonstrating superior effectiveness and robustness compared to existing approaches. On the reasoning-intensive BRIGHT benchmark, our ERank-4B achieves an nDCG@10 of 38.7, while a larger 32B variant reaches a state of the art nDCG@10 of 40.2.