mlsanityData to 14 Oct 2026

BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination

arXiv 2604.08834 ↗First posted 10 Apr 2026cs.IRcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Reasoning-intensive retrieval requires deep semantic inference beyond surface-level keyword matching, posing a challenge for current LLM-based rerankers limited by context constraints and order sensitivity. We propose BracketRank, a framework that treats document reranking as a reasoning-driven competitive tournament. Our approach introduces three key innovations: (1) adaptive grouping based on model context limits, (2) reasoning-enhanced prompts that mandate step-by-step relevance explanations, and (3) a bracket-style elimination structure with winner and loser tracks. This design ensures robust document advancement while enabling parallel processing across competition stages. Evaluation on the BRIGHT reasoning benchmark shows that BracketRank achieves 26.56 nDCG@10, significantly outperforming state-of-the-art baselines including RankGPT-4 (17.0) and Rank-R1-14B (20.5). On TREC datasets, BracketRank achieves 77.90 nDCG@5 on DL 19 and 75.85 nDCG@5 on DL 20, exceeding all baselines, establishing that explicit reasoning within competitive elimination is a powerful paradigm for complex, multi-step retrieval tasks. https://github.com/DataScienceUIBK/BracketRank

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 30 of its 30 references that are in the map. First posted on arXiv 10 Apr 2026.

Builds on

30 of 30 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval14 Jan
  2. 2025DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation23 Aug
  3. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning8 Mar

Other references · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  5. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  6. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  8. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  9. 2019Passage Re-ranking with BERTcited by 645
  10. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  11. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
  12. 2020Overview of the TREC 2019 deep learning trackcited by 286
15 more
  1. 2021Overview of the TREC 2020 deep learning trackcited by 196
  2. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 165
  3. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 155
  4. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 115
  5. 2023Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labelscited by 86
  6. 2021The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Modelscited by 81
  7. 2021Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representationscited by 60
  8. 2024TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategycited by 47
  9. 2024ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrievalcited by 30
  10. 2024DemoRank: Selecting Effective Demonstrations for Large Language Models in Ranking Taskcited by 17
  11. 2026MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrievalcited by 11
  12. 2025ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrievalcited by 9
  13. 2024MCRanker: Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankerscited by 7
  14. 2026RECOR: Reasoning-focused Multi-turn Conversational Retrieval Benchmarkcited by 6
  15. 2025How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking
  2. 2024JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking
  3. 2025Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Short
  4. 2026Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning
  5. 2024ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation
  6. 2025Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking
  7. 2025Rank1: Test-Time Compute for Reranking in Information Retrieval
  8. 2026Adaptive Retrieval for Reasoning-Intensive Retrieval