Cover Image

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rao, Arjun, Alipour, Hanieh, Pendar, Nick
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ChatGPT Alternative Solutions: Large Language Models Survey
by: Alipour, Hanieh, et al.
Published: (2024)

Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models
by: Kelber, Florian, et al.
Published: (2026)

Modernizing Facebook Scoped Search: Keyword and Embedding Hybrid Retrieval with LLM Evaluation
by: Su, Yongye, et al.
Published: (2025)

LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding
by: Wu, Mingrui, et al.
Published: (2024)

Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking
by: Sager, Pascal J., et al.
Published: (2025)

ReBOL: Retrieval via Bayesian Optimization with Batched LLM Relevance Observations and Query Reformulation
by: Korikov, Anton, et al.
Published: (2026)

A Comparative Study of Text Retrieval Models on DaReCzech
by: Stetina, Jakub, et al.
Published: (2024)

A Preference-oriented Diversity Model Based on Mutual-information in Re-ranking for E-commerce Search
by: Wang, Huimu, et al.
Published: (2024)

HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data
by: Myung, Jiyoon, et al.
Published: (2025)

Chunking, Retrieval, and Re-ranking: An Empirical Evaluation of RAG Architectures for Policy Document Question Answering
by: Maharjan, Anuj, et al.
Published: (2026)

Enhancing Retrieval-Augmented Generation with Topic-Enriched Embeddings: A Hybrid Approach Integrating Traditional NLP Techniques
by: Kataishi, Rodrigo
Published: (2025)

A Hybrid Cross-Stage Coordination Pre-ranking Model for Online Recommendation Systems
by: Zhao, Binglei, et al.
Published: (2025)

RouterRetriever: Routing over a Mixture of Expert Embedding Models
by: Lee, Hyunji, et al.
Published: (2024)

Retrieval Collapses When AI Pollutes the Web
by: Yu, Hongyeon, et al.
Published: (2026)

One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States
by: Jiang, Bo
Published: (2026)

ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
by: Lin, Jianghao, et al.
Published: (2023)

When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models
by: Li, Yubo, et al.
Published: (2026)

Unified Embedding Based Personalized Retrieval in Etsy Search
by: Jha, Rishikesh, et al.
Published: (2023)

DynLLM: When Large Language Models Meet Dynamic Graph Recommendation
by: Zhao, Ziwei, et al.
Published: (2024)

LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation
by: He, Yingzhi, et al.
Published: (2025)

Synthetic Test Collections for Retrieval Evaluation
by: Rahmani, Hossein A., et al.
Published: (2024)

Hybrid Context Retrieval Augmented Generation Pipeline: LLM-Augmented Knowledge Graphs and Vector Database for Accreditation Reporting Assistance
by: Edwards, Candace
Published: (2024)

From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation at Industry Scale
by: Shi, Yucheng, et al.
Published: (2026)

pEBR: A Probabilistic Approach to Embedding Based Retrieval
by: Zhang, Han, et al.
Published: (2024)

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
by: Li, Zhuofeng, et al.
Published: (2026)

HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning
by: Bhattarai, Manish, et al.
Published: (2024)

Federated Recommendation via Hybrid Retrieval Augmented Generation
by: Zeng, Huimin, et al.
Published: (2024)

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
by: Astaraki, Mahdi, et al.
Published: (2026)

Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
by: Tian, Yuxing, et al.
Published: (2026)

FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation
by: An, Sohyun, et al.
Published: (2026)

LLM-Oriented Information Retrieval: A Denoising-First Perspective
by: Dai, Lu, et al.
Published: (2026)

A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search
by: Terrenzi, Riccardo, et al.
Published: (2026)

Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation
by: Ning, Liangbo, et al.
Published: (2025)

Guiding Retrieval using LLM-based Listwise Rankers
by: Rathee, Mandeep, et al.
Published: (2025)

DocReLM: Mastering Document Retrieval with Language Model
by: Wei, Gengchen, et al.
Published: (2024)

LLM-I2I: Boost Your Small Item2Item Recommendation Model with Large Language Model
by: Feng, Yinfu, et al.
Published: (2025)

Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
by: Zhang, Xiaoming, et al.
Published: (2024)

Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearning
by: Zhang, Haichao, et al.
Published: (2025)

Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search
by: Shen, Yedan, et al.
Published: (2025)

NR4DER: Neural Re-ranking for Diversified Exercise Recommendation
by: Cheng, Xinghe, et al.
Published: (2025)