pith. sign in

arxiv: 2503.06034 · v1 · pith:WBRFFGSCnew · submitted 2025-03-08 · 💻 cs.IR · cs.CL

Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning

classification 💻 cs.IR cs.CL
keywords rank-r1reasoningfine-tuningdatasetsllm-basedmethodsrankingrelevance
0
0 comments X
read the original abstract

In this paper, we introduce Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task. Existing document reranking methods based on large language models (LLMs) typically rely on prompting or fine-tuning LLMs to order or label candidate documents according to their relevance to a query. For Rank-R1, we use a reinforcement learning algorithm along with only a small set of relevance labels (without any reasoning supervision) to enhance the reasoning ability of LLM-based rerankers. Our hypothesis is that adding reasoning capabilities to the rerankers can improve their relevance assessement and ranking capabilities. Our experiments on the TREC DL and BRIGHT datasets show that Rank-R1 is highly effective, especially for complex queries. In particular, we find that Rank-R1 achieves effectiveness on in-domain datasets at par with that of supervised fine-tuning methods, but utilizing only 18\% of the training data used by the fine-tuning methods. We also find that the model largely outperforms zero-shot and supervised fine-tuning when applied to out-of-domain datasets featuring complex queries, especially when a 14B-size model is used. Finally, we qualitatively observe that Rank-R1's reasoning process improves the explainability of the ranking results, opening new opportunities for search engine results presentation and fruition.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Whole-Pool Setwise Reranking with Long-Context Language Models

    cs.IR 2026-06 unverdicted novelty 7.0

    DualEnd enables whole-pool setwise reranking of 100 candidates using 50 serial LLM calls by simultaneously selecting top and bottom passages with long-context models.

  2. Layer-wise Token Compression for Efficient Document Reranking

    cs.IR 2026-05 conditional novelty 7.0

    Layer-wise Token Compression applies adaptive pooling at middle transformer layers to increase QPS by up to 116% on document ranking with little or no loss in quality.

  3. Layer-wise Token Compression for Efficient Document Reranking

    cs.IR 2026-05 unverdicted novelty 7.0

    Layer-wise Token Compression applies adaptive token pooling at middle transformer layers for cross-encoder rerankers, preserving MS MARCO ranking quality while raising QPS up to 25% on passages and 116% on documents, ...

  4. F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking

    cs.LG 2026-05 unverdicted novelty 7.0

    F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked perfo...

  5. MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL

    cs.IR 2026-04 unverdicted novelty 7.0

    MARVEL reaches 37.9 nDCG@10 on the MM-BRIGHT benchmark by combining LLM query expansion, a reasoning-enhanced dense retriever, and GPT-4o CoT reranking, beating prior multimodal encoders by 10.3 points.

  6. A Survey of Reasoning-Intensive Retrieval: Progress and Challenges

    cs.IR 2026-04 unverdicted novelty 6.0

    A survey that categorizes RIR benchmarks by domain and modality, proposes a taxonomy for integrating reasoning into retrieval pipelines, and outlines key challenges.

  7. HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval

    cs.IR 2026-04 unverdicted novelty 6.0

    HIVE raises multimodal retrieval nDCG@10 to 41.7 on the MM-BRIGHT benchmark by inserting LLM-driven hypothesis generation and verification between retrieval passes, delivering +9.5 over the best text-only baseline and...

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

    cs.IR 2025-06 unverdicted novelty 6.0

    ProRank uses RL-based prompt warmup and fine-grained scoring to train small language models that surpass LLM rerankers on BEIR.

  9. Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models

    cs.CL 2026-06 unverdicted novelty 5.0

    DIA is a training-free method that dynamically adjusts anchor positions in diffusion LLMs to improve format compliance and accuracy on reasoning benchmarks like GSM8K and MATH.

  10. LRanker: LLM Ranker for Massive Candidates

    cs.IR 2026-05 unverdicted novelty 5.0

    LRanker combines K-means candidate aggregation with graph-partitioned ensemble of query embeddings to improve LLM ranking accuracy and scalability on massive candidate pools, reporting 3-30% gains on RBench tasks up t...

  11. Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking

    cs.IR 2026-04 unverdicted novelty 5.0

    AdaRankLLM shows adaptive listwise reranking outperforms fixed-depth retrieval for most LLMs by acting as a noise filter for weak models and an efficiency optimizer for strong ones, with lower context use.

  12. Rich-Media Re-Ranker: A User Satisfaction-Driven LLM Re-ranking Framework for Rich-Media Search

    cs.IR 2026-02 unverdicted novelty 5.0

    A re-ranking system for rich-media search that plans query intents from sessions, adds visual signals from VLMs, and uses an LLM to score results on multiple facets before multi-task RL adaptation, with reported gains...

  13. GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs

    cs.IR 2025-11 unverdicted novelty 5.0

    GroupRank uses groupwise LLM reranking with answer-free data synthesis and a group-ranking reward to reach 65.2 NDCG@10 on BRIGHT while providing 6.4x faster inference than listwise baselines.

  14. Reproducing Adaptive Reranking for Reasoning-Intensive IR

    cs.IR 2026-04 unverdicted novelty 2.0

    Reproducing GAR on BRIGHT shows it boosts reasoning-intensive retrieval effectiveness with low overhead when the reranker's signal quality is strong.