Yuanbao-Reranker: Document-Grounded Synthesis and Preference Distillation for Text Reranking
cs.IR
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/Yuanbao-Search/Yuanbao-Reranker
Terminology
Sources
- Passage Re-ranking with BERT
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking
- Promptagator: Few-shot Dense Retrieval From 8 Examples
- InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval
- Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- T2Ranking: A large-scale Chinese Benchmark for Passage Ranking
- When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
- Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation
- Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation
- Robust fine-tuning of zero-shot models
- C-Pack: Packed Resources For General Chinese Embeddings
- MMTEB: Massive Multilingual Text Embedding Benchmark
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking
- jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking
- jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation
- Distillation versus Contrastive Learning: How to Train Your Rerankers
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA