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

arXiv: https://arxiv.org/abs/2509.25085 · HTML: https://mlsanity.com/paper/2509.25085/

## 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 (most cited first, 24 of 24)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [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 are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering](https://mlsanity.com/paper/2007.15207/) (2020)
- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models](https://mlsanity.com/paper/2409.04701/) (2024)
- [RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models](https://mlsanity.com/paper/2309.15088/) (2023)
- [CoIR: A Comprehensive Benchmark for Code Information Retrieval Models](https://mlsanity.com/paper/2407.02883/) (2024)
- [FIRST: Faster Improved Listwise Reranking with Single Token Decoding](https://mlsanity.com/paper/2406.15657/) (2024)
- [BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers](https://mlsanity.com/paper/2404.18443/) (2024)
- [Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever](https://mlsanity.com/paper/2408.16672/) (2024)
- [Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models](https://mlsanity.com/paper/2406.14848/) (2024)
- [A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE](https://mlsanity.com/paper/2403.10407/) (2024)
- [PyLate: Flexible Training and Retrieval for Late Interaction Models](https://mlsanity.com/paper/2508.03555/) (2025)
- [DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation](https://mlsanity.com/paper/2508.16998/) (2025)
- [An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models](https://mlsanity.com/paper/2403.13291/) (2024)
- [Efficient and Effective Tree-based and Neural Learning to Rank](https://mlsanity.com/paper/2305.08680/) (2023)
- [Efficient Document Ranking with Learnable Late Interactions](https://mlsanity.com/paper/2406.17968/) (2024)
- [ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking](https://mlsanity.com/paper/2509.00520/) (2025)
- [Contrastive Learning with Negative Sampling Correction](https://mlsanity.com/paper/2401.08690/) (2024)

## Built on by (most cited first, 24 of 24)

- [Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use](https://mlsanity.com/paper/2604.05432/) (2026)
- [Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval](https://mlsanity.com/paper/2604.10167/) (2026)
- [LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2601.05192/) (2026)
- [OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understanding](https://mlsanity.com/paper/2602.13758/) (2026)
- [MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image](https://mlsanity.com/paper/2605.10616/) (2026)
- [Cross-modal Retrieval Models for Stripped Binary Analysis](https://mlsanity.com/paper/2512.10393/) (2025)
- [EnsembleLink: Accurate Record Linkage Without Training Data](https://mlsanity.com/paper/2601.21138/) (2026)
- [His2Trans: A Knowledge-Guided Agentic Framework for Project-Level C-to-Rust Migration](https://mlsanity.com/paper/2603.02617/) (2026)
- [Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval](https://mlsanity.com/paper/2604.23734/) (2026)
- [EmbeddingRWKV: State-Centric Retrieval with Reusable States](https://mlsanity.com/paper/2601.07861/) (2026)
- [UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidates](https://mlsanity.com/paper/2603.29897/) (2026)
- [ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression](https://mlsanity.com/paper/2604.22180/) (2026)
- [DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking](https://mlsanity.com/paper/2605.18767/) (2026)
- [Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of Service](https://mlsanity.com/paper/2605.26019/) (2026)
- [Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking](https://mlsanity.com/paper/2606.22807/) (2026)
- [LAMAR: An Open Language-Aware Multilingual Alignment Reranker](https://mlsanity.com/paper/2607.22042/) (2026)
- [A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility](https://mlsanity.com/paper/2607.24663/) (2026)
- [Hierarchical Reranking for Scalable Financial RAG System](https://mlsanity.com/paper/2607.27523/) (2026)
- [UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2608.01147/) (2026)
- [Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers](https://mlsanity.com/paper/2608.26762/) (2026)
- [CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation](https://mlsanity.com/paper/2609.04083/) (2026)
- [TableSeek: Structure-Preserving Agentic Evidence Seeking over Heterogeneous Table Corpora](https://mlsanity.com/paper/2609.34157/) (2026)
- [Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search](https://mlsanity.com/paper/2610.11922/) (2026)
- [FunDM: Cheap & Label-Free Decision Models from Frozen Language Models](https://mlsanity.com/paper/2610.17175/) (2026)

## 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.