SPARSEUP: Towards Better Recipes for Training Modern Learned Sparse Retrievers
cs.IR
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Granite Embedding Models
- Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies
- Rescaling MLM-Head for Neural Sparse Retrieval
- ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search
- FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents
- EmbeddingGemma: Powerful and Lightweight Text Representations
- LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum
Related papers
- 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
- One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations