Cover Image

Training for Compositional Sensitivity Reduces Dense Retrieval Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ralev, Radoslav, Baral, Aditeya, Zhechev, Iliya, Agarwal, Jen, Rajamohan, Srijith
Format:	Preprint
Published:	2026
Subjects:	Information Retrieval Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
by: Thakur, Nandan, et al.
Published: (2023)

Dense X Retrieval: What Retrieval Granularity Should We Use?
by: Chen, Tong, et al.
Published: (2023)

MultiContrievers: Analysis of Dense Retrieval Representations
by: Goldfarb-Tarrant, Seraphina, et al.
Published: (2024)

Spectral Tempering for Embedding Compression in Dense Passage Retrieval
by: Li, Yongkang, et al.
Published: (2026)

Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling
by: Zhang, Hengran, et al.
Published: (2025)

QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval
by: Tan, Hongming, et al.
Published: (2024)

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
by: Xu, Shicheng, et al.
Published: (2024)

WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval
by: Dinzinger, Michael, et al.
Published: (2025)

DR.EHR: Dense Retrieval for Electronic Health Record with Knowledge Injection and Synthetic Data
by: Zhao, Zhengyun, et al.
Published: (2025)

Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies
by: Clavié, Benjamin, et al.
Published: (2026)

MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers
by: Kalra, Jushaan Singh, et al.
Published: (2025)

TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval
by: Ezerceli, Özay, et al.
Published: (2025)

WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval
by: Dinzinger, Michael, et al.
Published: (2026)

VERA: Validation and Enhancement for Retrieval Augmented systems
by: Birur, Nitin Aravind, et al.
Published: (2024)

Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
by: Clavié, Benjamin, et al.
Published: (2024)

Training-Induced Bias Toward LLM-Generated Content in Dense Retrieval
by: Xion, William, et al.
Published: (2026)

Reducing hallucination in structured outputs via Retrieval-Augmented Generation
by: Béchard, Patrice, et al.
Published: (2024)

Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
by: Chen, Weishu, et al.
Published: (2026)

Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation
by: Zhang, Hengran, et al.
Published: (2025)

Distillation Enhanced Generative Retrieval
by: Li, Yongqi, et al.
Published: (2024)

R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation
by: Ye, Fuda, et al.
Published: (2024)

A Comparative Study of Specialized LLMs as Dense Retrievers
by: Zhang, Hengran, et al.
Published: (2025)

Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval
by: Pang, Ming, et al.
Published: (2025)

Benchmarking Retrieval-Augmented Generation for Chemistry
by: Zhong, Xianrui, et al.
Published: (2025)

From Matching to Generation: A Survey on Generative Information Retrieval
by: Li, Xiaoxi, et al.
Published: (2024)

Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback
by: Jedidi, Nour, et al.
Published: (2024)

LLatrieval: LLM-Verified Retrieval for Verifiable Generation
by: Li, Xiaonan, et al.
Published: (2023)

Retrieval-Augmented Generation by Evidence Retroactivity in LLMs
by: Xiao, Liang, et al.
Published: (2025)

Graph Retrieval-Augmented Generation: A Survey
by: Peng, Boci, et al.
Published: (2024)

Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs
by: Thakur, Nandan, et al.
Published: (2025)

RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish
by: Köse, Süha Kağan, et al.
Published: (2026)

Enhancing Retrieval Processes for Language Generation with Augmented Queries
by: Ghali, Julien Pierre Edmond, et al.
Published: (2024)

PISCO: Pretty Simple Compression for Retrieval-Augmented Generation
by: Louis, Maxime, et al.
Published: (2025)

Neural Retrievers are Biased Towards LLM-Generated Content
by: Dai, Sunhao, et al.
Published: (2023)

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
by: Zhou, Yujia, et al.
Published: (2024)

Event GDR: Event-Centric Generative Document Retrieval
by: Guan, Yong, et al.
Published: (2024)

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models
by: Peng, Zhiyuan, et al.
Published: (2023)

Generative Language Models with Retrieval Augmented Generation for Automated Short Answer Scoring
by: Wang, Zifan, et al.
Published: (2024)

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
by: Sawarkar, Kunal, et al.
Published: (2024)

GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation
by: Luo, Linhao, et al.
Published: (2025)