15 citations · 51 across the 21 of their papers we have counts for
21 papers
On the Challenges and Opportunities of Learned Sparse Retrieval for Code
Simon Lupart, Maxime Louis, Thibault Formal +2
Retrieval over large codebases is a key component of modern LLM-based software engineering systems. Existing approaches predominantly rely on dense embedding models, while learned…
Learning Retrieval Models with Sparse Autoencoders
Thibault Formal, Maxime Louis, Hervé Dejean +1
Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We po…
Naver Labs Europe @ WSDM CUP | Multilingual Retrieval
Thibault Formal, Maxime Louis, Hervé Déjean +1
This report presents our participation to the WSDM Cup 2026 shared task on multilingual document retrieval from English queries. The task provides a challenging benchmark for cross…
XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation
Youssef Mohamed, Mohamed Elhoseiny, Thibault Formal +1
This paper introduces XProvence, a multilingual zero-cost context pruning model for retrieval-augmented generation (RAG), trained on 16 languages and supporting 100+ languages thro…
OSCAR: Online Soft Compression And Reranking
Maxime Louis, Thibault Formal, Hervé Dejean +1
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge, leading to improved accuracy and relevance. However, scaling RAG pipel…
Provence: efficient and robust context pruning for retrieval-augmented generation
Nadezhda Chirkova, Thibault Formal, Vassilina Nikoulina +1
Retrieval-augmented generation improves various aspects of large language models (LLMs) generation, but suffers from computational overhead caused by long contexts as well as the p…
Retrieval-augmented generation in multilingual settings
Nadezhda Chirkova, David Rau, Hervé Déjean +3
Retrieval-augmented generation (RAG) has recently emerged as a promising solution for incorporating up-to-date or domain-specific knowledge into large language models (LLMs) and im…
BERGEN: A Benchmarking Library for Retrieval-Augmented Generation
David Rau, Hervé Déjean, Nadezhda Chirkova +4
Retrieval-Augmented Generation allows to enhance Large Language Models with external knowledge. In response to the recent popularity of generative LLMs, many RAG approaches have be…
SPLATE: Sparse Late Interaction Retrieval
Thibault Formal, Stéphane Clinchant, Hervé Déjean +1
The late interaction paradigm introduced with ColBERT stands out in the neural Information Retrieval space, offering a compelling effectiveness-efficiency trade-off across many ben…
A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE
Hervé Déjean, Stéphane Clinchant, Thibault Formal
We present a comparative study between cross-encoder and LLMs rerankers in the context of re-ranking effective SPLADE retrievers. We conduct a large evaluation on TREC Deep Learnin…
SPLADE-v3: New baselines for SPLADE
Carlos Lassance, Hervé Déjean, Thibault Formal +1
A companion to the release of the latest version of the SPLADE library. We describe changes to the training structure and present our latest series of models -- SPLADE-v3. We compa…
Benchmarking Middle-Trained Language Models for Neural Search
Hervé Déjean, Stéphane Clinchant, Carlos Lassance +2
Middle training methods aim to bridge the gap between the Masked Language Model (MLM) pre-training and the final finetuning for retrieval. Recent models such as CoCondenser, RetroM…
Query Performance Prediction for Neural IR: Are We There Yet?
Guglielmo Faggioli, Thibault Formal, Stefano Marchesin +3
Evaluation in Information Retrieval relies on post-hoc empirical procedures, which are time-consuming and expensive operations. To alleviate this, Query Performance Prediction (QPP…
CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval
Nam Le Hai, Thomas Gerald, Thibault Formal +3
Conversational search is a difficult task as it aims at retrieving documents based not only on the current user query but also on the full conversation history. Most of the previou…
From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective
Thibault Formal, Carlos Lassance, Benjamin Piwowarski +1
Neural retrievers based on dense representations combined with Approximate Nearest Neighbors search have recently received a lot of attention, owing their success to distillation a…
MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrieval
Simon Lupart, Thibault Formal, Stéphane Clinchant
Pre-trained Language Models have recently emerged in Information Retrieval as providing the backbone of a new generation of neural systems that outperform traditional methods on a…
Composite Code Sparse Autoencoders for first stage retrieval
Carlos Lassance, Thibault Formal, Stephane Clinchant
We propose a Composite Code Sparse Autoencoder (CCSA) approach for Approximate Nearest Neighbor (ANN) search of document representations based on Siamese-BERT models. In Informatio…
Match Your Words! A Study of Lexical Matching in Neural Information Retrieval
Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant
Neural Information Retrieval models hold the promise to replace lexical matching models, e.g. BM25, in modern search engines. While their capabilities have fully shone on in-domain…
SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval
Thibault Formal, Carlos Lassance, Benjamin Piwowarski +1
In neural Information Retrieval (IR), ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using…
SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking
Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant
In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using effic…
A White Box Analysis of ColBERT
Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant
Transformer-based models are nowadays state-of-the-art in ad-hoc Information Retrieval, but their behavior is far from being understood. Recent work has claimed that BERT does not…