Imagen de Portada

OSCAR: Online Soft Compression And Reranking

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Louis, Maxime, Formal, Thibault, Dejean, Hervé, Clinchant, Stéphane
Formato:	Preprint
Publicado:	2025
Materias:	Information Retrieval Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Learning Retrieval Models with Sparse Autoencoders
por: Formal, Thibault, et al.
Publicado: (2026)

A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE
por: Déjean, Hervé, et al.
Publicado: (2024)

On the Challenges and Opportunities of Learned Sparse Retrieval for Code
por: Lupart, Simon, et al.
Publicado: (2026)

SPLADE-v3: New baselines for SPLADE
por: Lassance, Carlos, et al.
Publicado: (2024)

Naver Labs Europe @ WSDM CUP | Multilingual Retrieval
por: Formal, Thibault, et al.
Publicado: (2026)

Reranking with Compressed Document Representation
por: Déjean, Hervé, et al.
Publicado: (2025)

Efficient Listwise Reranking with Compressed Document Representations
por: Déjean, Hervé, et al.
Publicado: (2026)

SPLATE: Sparse Late Interaction Retrieval
por: Formal, Thibault, et al.
Publicado: (2024)

BERGEN: A Benchmarking Library for Retrieval-Augmented Generation
por: Rau, David, et al.
Publicado: (2024)

Provence: efficient and robust context pruning for retrieval-augmented generation
por: Chirkova, Nadezhda, et al.
Publicado: (2025)

Context Embeddings for Efficient Answer Generation in RAG
por: Rau, David, et al.
Publicado: (2024)

Retrieval-augmented generation in multilingual settings
por: Chirkova, Nadezhda, et al.
Publicado: (2024)

Two-Step SPLADE: Simple, Efficient and Effective Approximation of SPLADE
por: Lassance, Carlos, et al.
Publicado: (2024)

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
por: Wu, Yuhang, et al.
Publicado: (2026)

Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective
por: Liu, Yunhao, et al.
Publicado: (2026)

XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation
por: Mohamed, Youssef, et al.
Publicado: (2026)

List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation
por: Xu, Shicheng, et al.
Publicado: (2024)

Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
por: Park, Sangkwon, et al.
Publicado: (2026)

FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering
por: Zhou, Yixi, et al.
Publicado: (2026)

E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
por: Liu, Qi, et al.
Publicado: (2025)

PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking Mechanism
por: Li, Ningyuan, et al.
Publicado: (2025)

InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filtering
por: Wang, Zihan, et al.
Publicado: (2025)

Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications
por: Rumble, Teri, et al.
Publicado: (2025)

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
por: Jedidi, Nour, et al.
Publicado: (2025)

Improving Bilingual Lexicon Induction with Cross-Encoder Reranking
por: Li, Yaoyiran, et al.
Publicado: (2022)

AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
por: Yoon, Soyoung, et al.
Publicado: (2025)

Efficient Title Reranker for Fast and Improved Knowledge-Intense NLP
por: Chen, Ziyi, et al.
Publicado: (2023)

Solving the Content Gap in Roblox Game Recommendations: LLM-Based Profile Generation and Reranking
por: Wang, Chen, et al.
Publicado: (2025)

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

Retrieval-Augmented LLM Agents: Learning to Learn from Experience
por: Ferraz, Thomas Palmeira, et al.
Publicado: (2026)

SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
por: Jin, Yiqiao, et al.
Publicado: (2025)

ECoRAG: Evidentiality-guided Compression for Long Context RAG
por: Jeong, Yeonseok, et al.
Publicado: (2025)

Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
por: Xi, Yunjia, et al.
Publicado: (2026)

Q-PEFT: Query-dependent Parameter Efficient Fine-tuning for Text Reranking with Large Language Models
por: Peng, Zhiyuan, et al.
Publicado: (2024)

EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation
por: Hwang, Taeho, et al.
Publicado: (2024)

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
por: Cheng, Xin, et al.
Publicado: (2024)

Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference
por: Kummer, Cornelius, et al.
Publicado: (2026)

Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning
por: Eponon, Anvi Alex, et al.
Publicado: (2025)

Recommending Clinical Trials for Online Patient Cases using Artificial Intelligence
por: Chan, Joey, et al.
Publicado: (2025)