Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens
cs.IR
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- EuroBERT: Scaling Multilingual Encoders for European Languages
- NeoBERT: A Next-Generation BERT
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- LMK > CLS: Landmark Pooling for Dense Embeddings
- Quantifying Positional Biases in Text Embedding Models
- Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks
- Massive Activations in Large Language Models
- Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs
- Seq vs Seq: An Open Suite of Paired Encoders and Decoders
- mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
- LongEmbed: Extending Embedding Models for Long Context Retrieval
- JTCSE: Joint Tensor-Modulus Constraints and Cross-Attention for Unsupervised Contrastive Learning of Sentence Embeddings
- Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
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