Cover Image

From Tokens to Concepts: Leveraging SAE for SPLADE

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zong, Yuxuan, Vast, Mathias, Van Cooten, Basile, Soulier, Laure, Piwowarski, Benjamin
Format:	Preprint
Published:	2026
Subjects:	Information Retrieval Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Simple Domain Adaptation for Sparse Retrievers
by: Vast, Mathias, et al.
Published: (2024)

Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders
by: Vast, Mathias, et al.
Published: (2024)

Understanding Matching Mechanisms in Cross-Encoders
by: Vast, Mathias, et al.
Published: (2025)

Reproducing and Comparing Distillation Techniques for Cross-Encoders
by: Morand, Victor, et al.
Published: (2026)

MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking
by: Vast, Mathias, et al.
Published: (2026)

Towards Lossless Token Pruning in Late-Interaction Retrieval Models
by: Zong, Yuxuan, et al.
Published: (2025)

CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval
by: Hai, Nam Le, et al.
Published: (2023)

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

Navigating Uncertainty: Optimizing API Dependency for Hallucination Reduction in Closed-Book Question Answering
by: Erbacher, Pierre, et al.
Published: (2024)

An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doc
by: Porco, Aldo, et al.
Published: (2025)

Mistral-SPLADE: LLMs for better Learned Sparse Retrieval
by: Doshi, Meet, et al.
Published: (2024)

PAQA: Toward ProActive Open-Retrieval Question Answering
by: Erbacher, Pierre, et al.
Published: (2024)

The Pre-Training Study of Expanded-SPLADE Models on Web Document Titles
by: Kim, Hiun, et al.
Published: (2026)

RAC: Retrieval-Augmented Clarification for Faithful Conversational Search
by: Kebir, Ahmed Rayane, et al.
Published: (2026)

QueStER: Query Specification for Generative keyword-based Retrieval
by: Satouf, Arthur, et al.
Published: (2025)

A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models
by: Kankanampati, Yash, et al.
Published: (2026)

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

Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse Retrieval
by: Satouf, Arthur, et al.
Published: (2025)

xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation
by: Musacchio, Elio, et al.
Published: (2025)

Clarifying Ambiguities: on the Role of Ambiguity Types in Prompting Methods for Clarification Generation
by: Tang, Anfu, et al.
Published: (2025)

HeceTokenizer: A Syllable-Based Tokenization Approach for Turkish Retrieval
by: Gulgonul, Senol
Published: (2026)

Text2Token: Unsupervised Text Representation Learning with Token Target Prediction
by: An, Ruize, et al.
Published: (2025)

Contextualization with SPLADE for High Recall Retrieval
by: Yang, Eugene
Published: (2024)

NevIR: Negation in Neural Information Retrieval
by: Weller, Orion, et al.
Published: (2023)

PromptLink: Leveraging Large Language Models for Cross-Source Biomedical Concept Linking
by: Xie, Yuzhang, et al.
Published: (2024)

A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens
by: Nie, Zhijie, et al.
Published: (2024)

Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition
by: Liu, Shanshan, et al.
Published: (2026)

Multi-Field Adaptive Retrieval
by: Li, Millicent, et al.
Published: (2024)

Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
by: Lee, Jinhyuk, et al.
Published: (2023)

ConExion: Concept Extraction with Large Language Models
by: Norouzi, Ebrahim, et al.
Published: (2025)

Token and Span Classification for Entity Recognition in French Historical Encyclopedias
by: Moncla, Ludovic, et al.
Published: (2025)

Defending Against Disinformation Attacks in Open-Domain Question Answering
by: Weller, Orion, et al.
Published: (2022)

FIT-RAG: Black-Box RAG with Factual Information and Token Reduction
by: Mao, Yuren, et al.
Published: (2024)

Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens
by: Albarede, Lucas, et al.
Published: (2025)

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

Improving Retrieval in Sponsored Search by Leveraging Query Context Signals
by: Mohankumar, Akash Kumar, et al.
Published: (2024)

FGR-ColBERT: Identifying Fine-Grained Relevance Tokens During Retrieval
by: Jarolím, Antonín, et al.
Published: (2026)

An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking
by: Chen, Zijian, et al.
Published: (2024)

Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
by: Liu, Qi, et al.
Published: (2024)

Towards Fair Rankings: Leveraging LLMs for Gender Bias Detection and Measurement
by: Mousavian, Maryam, et al.
Published: (2025)