mlsanityData to 14 Oct 2026

jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking

arXiv 2509.25085 ↗First posted 29 Sep 2025cs.CL cs.AI cs.IRcited by 24

Not on the map. Why?

Abstract (arXiv)

jina-reranker-v3 is a 0.6B-parameter multilingual listwise reranker that introduces a novel "last but not late" interaction. Unlike late interaction models like ColBERT that encode documents separately before multi-vector matching, our approach applies causal attention between the query and all candidate documents in the same context window, enabling rich interactions before extracting contextual embeddings from each document's final token. The new model achieves state-of-the-art BEIR performance with 61.94 nDCG@10 while being significantly smaller than other models with comparable performance.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 24 of its 29 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

24 of 29 references.

References · 24

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  4. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  5. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  6. 2019Passage Re-ranking with BERTcited by 645
  7. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
  8. 2020MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answeringcited by 153
  9. 2021mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Datasetcited by 116
  10. 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Modelscited by 73
  11. 2023RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Modelscited by 70
  12. 2024CoIR: A Comprehensive Benchmark for Code Information Retrieval Modelscited by 60
12 more
  1. 2024FIRST: Faster Improved Listwise Reranking with Single Token Decodingcited by 54
  2. 2024BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrieverscited by 38
  3. 2024Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retrievercited by 25
  4. 2024Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Modelscited by 20
  5. 2024A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADEcited by 18
  6. 2025PyLate: Flexible Training and Retrieval for Late Interaction Modelscited by 18
  7. 2025DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillationcited by 11
  8. 2024An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Modelscited by 7
  9. 2023Efficient and Effective Tree-based and Neural Learning to Rankcited by 6
  10. 2024Efficient Document Ranking with Learnable Late Interactionscited by 6
  11. 2025ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Rerankingcited by 6
  12. 2024Contrastive Learning with Negative Sampling Correctioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 23.

24 papers.

Sort:

By area:

  1. 2026Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Usecited by 10
  2. 2026Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrievalcited by 8
  3. 2026LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptationcited by 6
  4. 2026OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understandingcited by 5
  5. 2026MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Imagecited by 2
  6. 2025Cross-modal Retrieval Models for Stripped Binary Analysiscited by 1
  7. 2026EnsembleLink: Accurate Record Linkage Without Training Datacited by 1
  8. 2026His2Trans: A Knowledge-Guided Agentic Framework for Project-Level C-to-Rust Migrationcited by 1
  9. 2026Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrievalcited by 1
  10. 2026EmbeddingRWKV: State-Centric Retrieval with Reusable Statescited by 0
  11. 2026UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidatescited by 0
  12. 2026ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compressioncited by 0
12 more
  1. 2026DualView: Adaptive Local-Global Fusion for Multi-Hop Document Rerankingcited by 0
  2. 2026Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of Servicecited by 0
  3. 2026Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Rerankingcited by 0
  4. 2026LAMAR: An Open Language-Aware Multilingual Alignment Rerankercited by 0
  5. 2026A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facilitycited by 0
  6. 2026Hierarchical Reranking for Scalable Financial RAG Systemcited by 0
  7. 2026UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answeringcited by 0
  8. 2026Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorerscited by 0
  9. 2026CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillationcited by 0
  10. 2026TableSeek: Structure-Preserving Agentic Evidence Seeking over Heterogeneous Table Corporacited by 0
  11. 2026Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Searchcited by 0
  12. 2026FunDM: Cheap & Label-Free Decision Models from Frozen Language Modelscited by 0