arXiv subjects

Stéphane Clinchant

Publications and source records attributed to Stéphane Clinchant.

At least 19 recordsLinked to original sources

arXiv2026

Retrieval-Augmented LLM Agents: Learning to Learn from Experience

While large language models (LLMs) have advanced the development of general-purpose agents, robust generalization to unseen tasks remains challenging. Two common approaches are supervised fine-tuning and training-free memory-augmented generation using retrieved experience; yet both have limitations: fine-tuning often fails to extrapolate to new tasks, while experience retrieval often underperforms compared to supervised baselines. In this work, we combine these approaches and study how retrieval-augmented LLM agents can learn to use retrieved trajectories in-context. First, we establish a strong LoRA fine-tuning baseline that outperforms several state-of-the-art agent training pipelines. Second, we analyze key design choices for experience retrieval, including storage, querying, and trajectory selection. We then integrate experience retrieval directly into the fine-tuning process, finding that this substantially improves generalization to unseen tasks. Finally, we show that these gains often persist with imperfect experience and, even when agents reuse their own failed attempts without test-time parameter updates. Overall, our results establish simple episodic retrieval as a strong foundation for agent memory and retrieval-aware fine-tuning as a practical and effective framework for building agents that learn to learn from experience.

cs.AI↗

arXiv2026

Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search

As large-scale visual-document corpora such as arXiv papers and enterprise PDFs continue to grow, visual-document retrieval has gained increasing attention; yet it still lacks a deployable system that lexically indexes visual documents to serve queries without neural encoding at scale. Existing methods either achieve strong retrieval quality with VLM-based dense or multi-vector models but require neural query encoding at serving time, or avoid query encoding with OCR- or caption-based BM25 at the cost of time-consuming text extraction or generation. To fill this missing serving regime, we present V-SPLADE, an inference-free sparse retriever for visual-document retrieval. However, such inference-free multimodal learned sparse retrieval systems remain underexplored and have not yet shown dense-level effectiveness under high sparsity. We attribute this limitation to a lexical grounding problem: visual sparse representations often fail to capture the lexical content embedded in document images. To address this problem, we introduce caption-gated token supervision, a training-only signal that uses VLM-generated captions as lexical cues to activate retrieval-relevant vocabulary dimensions. With this supervision, V-SPLADE improves average NDCG@5 across six visual-document retrieval benchmarks by +13.8pp over the same-scale dense baseline and by up to +6.3pp over OCR- or caption-based BM25 baselines. On an 18.7M-document corpus, it more than doubles R@5 over the same-scale dense baseline and further improves competing retrievers through score fusion by up to +2.4pp R@5. Code will be released soon at https://github.com/naver/v-splade.

cs.IR↗

arXiv2026

Efficient Listwise Reranking with Compressed Document Representations

Reranking, the process of refining the output from a first-stage retriever, is often considered computationally expensive, especially when using Large Language Models (LLMs). A common approach to mitigate this cost involves utilizing smaller LLMs or controlling input length. Inspired by recent advances in document compression for retrieval-augmented generation (RAG), we introduce RRK, an efficient and effective listwise reranker compressing documents into multi-token fixed-size embedding representations. Our simple training via distillation shows that this combination of rich compressed representations and listwise reranking yields a highly efficient and effective system. In particular, our 8B-parameter model runs 3x-18x faster than smaller rerankers (0.6-4B parameters) while matching or outperforming them in effectiveness. The efficiency gains are even more striking on long-document benchmarks, where RRK widens its advantage further.

cs.IR↗

arXiv2026

On the Challenges and Opportunities of Learned Sparse Retrieval for Code

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 sparse retrieval (LSR) remains largely unexplored for code. However, applying sparse retrieval to code is challenging due to subword fragmentation, semantic gaps between natural-language queries and code, diversity of programming languages and sub-tasks, and the length of code documents, which can harm sparsity and latency. We introduce SPLADE-Code, the first large-scale family of learned sparse retrieval models specialized for code retrieval (600M-8B parameters). Despite a lightweight one-stage training pipeline, SPLADE-Code achieves state-of-the-art performance among retrievers under 1B parameters (75.4 on MTEB Code) and competitive results at larger scales (79.0 with 8B). We show that learned expansion tokens are critical to bridge lexical and semantic matching, and provide a latency analysis showing that LSR enables sub-millisecond retrieval on a 1M-passage collection with little effectiveness loss.

cs.IR↗

arXiv2026

OSCAR: Online Soft Compression And Reranking

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge, leading to improved accuracy and relevance. However, scaling RAG pipelines remains computationally expensive as retrieval sizes grow. To address this, we introduce OSCAR, a novel query-dependent online soft compression method that reduces computational overhead while preserving performance. Unlike traditional hard compression methods, which shorten retrieved texts, or soft compression approaches, which map documents to continuous embeddings offline, OSCAR dynamically compresses retrieved information at inference time, eliminating storage overhead and enabling higher compression rates. Additionally, we extend OSCAR to simultaneously perform reranking, further optimizing the efficiency of the RAG pipeline. Our experiments demonstrate state-of-the-art performance with a 2-5x speed-up in inference and minimal to no loss in accuracy for LLMs ranging from 1B to 24B parameters. The models are available at: https://huggingface.co/collections/naver/oscar-67d446a8e3a2551f57464295.

cs.IR↗

arXiv2026

Learning Retrieval Models with Sparse Autoencoders

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned Sparse Retrieval (LSR), whose objective is to encode queries and documents into high-dimensional sparse representations optimized for efficient retrieval. In contrast to existing LSR approaches that project input sequences into the vocabulary space, SAE-based representations offer the potential to produce more semantically structured, expressive, and language-agnostic features. Building on this insight, we introduce SPLARE, a method to train SAE-based LSR models. Our experiments, relying on recently released open-source SAEs, demonstrate that this technique consistently outperforms vocabulary-based LSR in multilingual and out-of-domain settings. SPLARE-7B, a multilingual retrieval model capable of producing generalizable sparse latent embeddings for a wide range of languages and domains, achieves top results on MMTEB's multilingual and English retrieval tasks. We also developed a 2B-parameter variant with a significantly lighter footprint.

cs.LG↗

arXiv2026

Naver Labs Europe @ WSDM CUP | Multilingual Retrieval

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-lingual generalization. It also provides a natural testbed for evaluating SPLARE, our recently proposed learned sparse retrieval model, which produces generalizable sparse latent representations and is particularly well suited to multilingual retrieval settings. We evaluate five progressively enhanced runs, starting from a SPLARE-7B model and incorporating lightweight improvements, including reranking with Qwen3-Reranker-4B and simple score fusion strategies. Our results demonstrate the strength of SPLARE compared to state-of-the-art dense baselines such as Qwen3-8B-Embed. More broadly, our submission highlights the continued relevance and competitiveness of learned sparse retrieval models beyond English-centric scenarios.

cs.IR↗

arXiv2025

RANa: Retrieval-Augmented Navigation

Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While these generalization capabilities to an unknown environment are extremely important, we claim that, in a realistic setting, an agent should have the capacity of exploiting information collected during earlier robot operations. We address this by introducing a new retrieval-augmented agent, trained with RL, capable of querying a database collected from previous episodes in the same environment and learning how to integrate this additional context information. We introduce a unique agent architecture for the general navigation task, evaluated on ImageNav, Instance-ImageNav and ObjectNav. Our retrieval and context encoding methods are data-driven and employ vision foundation models (FM) for both semantic and geometric understanding. We propose new benchmarks for these settings and we show that retrieval allows zero-shot transfer across tasks and environments while significantly improving performance.

cs.CV↗

arXiv2025

Reranking with Compressed Document Representation

Reranking, the process of refining the output of a first-stage retriever, is often considered computationally expensive, especially with Large Language Models. Borrowing from recent advances in document compression for RAG, we reduce the input size by compressing documents into fixed-size embedding representations. We then teach a reranker to use compressed inputs by distillation. Although based on a billion-size model, our trained reranker using this compressed input can challenge smaller rerankers in terms of both effectiveness and efficiency, especially for long documents. Given that text compressors are still in their early development stages, we view this approach as promising.

cs.IR↗

arXiv2025

PISCO: Pretty Simple Compression for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs and limited context size. Document compression is a practical solution, but current soft compression methods suffer from accuracy losses and require extensive pretraining. In this paper, we introduce PISCO, a novel method that achieves a 16x compression rate with minimal accuracy loss (0-3%) across diverse RAG-based question-answering (QA) tasks. Unlike existing approaches, PISCO requires no pretraining or annotated data, relying solely on sequence-level knowledge distillation from document-based questions. With the ability to fine-tune a 7-10B LLM in 48 hours on a single A100 GPU, PISCO offers a highly efficient and scalable solution. We present comprehensive experiments showing that PISCO outperforms existing compression models by 8% in accuracy.

cs.CL↗

arXiv2025

Provence: efficient and robust context pruning for retrieval-augmented generation

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 propagation of irrelevant retrieved information into generated responses. Context pruning deals with both aspects, by removing irrelevant parts of retrieved contexts before LLM generation. Existing context pruning approaches are however limited, and do not provide a universal model that would be both efficient and robust in a wide range of scenarios, e.g., when contexts contain a variable amount of relevant information or vary in length, or when evaluated on various domains. In this work, we close this gap and introduce Provence (Pruning and Reranking Of retrieVEd relevaNt ContExts), an efficient and robust context pruner for Question Answering, which dynamically detects the needed amount of pruning for a given context and can be used out-of-the-box for various domains. The three key ingredients of Provence are formulating the context pruning task as sequence labeling, unifying context pruning capabilities with context reranking, and training on diverse data. Our experimental results show that Provence enables context pruning with negligible to no drop in performance, in various domains and settings, at almost no cost in a standard RAG pipeline. We also conduct a deeper analysis alongside various ablations to provide insights into training context pruners for future work.

cs.CL↗

arXiv2024

Context Embeddings for Efficient Answer Generation in RAG

Retrieval-Augmented Generation (RAG) allows overcoming the limited knowledge of LLMs by extending the input with external information. As a consequence, the contextual inputs to the model become much longer which slows down decoding time directly translating to the time a user has to wait for an answer. We address this challenge by presenting COCOM, an effective context compression method, reducing long contexts to only a handful of Context Embeddings speeding up the generation time by a large margin. Our method allows for different compression rates trading off decoding time for answer quality. Compared to earlier methods, COCOM allows for handling multiple contexts more effectively, significantly reducing decoding time for long inputs. Our method demonstrates a speed-up of up to 5.69 $\times$ while achieving higher performance compared to existing efficient context compression methods.

cs.CL↗

arXiv2024

BERGEN: A Benchmarking Library for Retrieval-Augmented Generation

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 been proposed, which involve an intricate number of different configurations such as evaluation datasets, collections, metrics, retrievers, and LLMs. Inconsistent benchmarking poses a major challenge in comparing approaches and understanding the impact of each component in the pipeline. In this work, we study best practices that lay the groundwork for a systematic evaluation of RAG and present BERGEN, an end-to-end library for reproducible research standardizing RAG experiments. In an extensive study focusing on QA, we benchmark different state-of-the-art retrievers, rerankers, and LLMs. Additionally, we analyze existing RAG metrics and datasets. Our open-source library BERGEN is available under \url{https://github.com/naver/bergen}.

cs.CL↗

arXiv2024

Retrieval-augmented generation in multilingual settings

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 improving LLM factuality, but is predominantly studied in English-only settings. In this work, we consider RAG in the multilingual setting (mRAG), i.e. with user queries and the datastore in 13 languages, and investigate which components and with which adjustments are needed to build a well-performing mRAG pipeline, that can be used as a strong baseline in future works. Our findings highlight that despite the availability of high-quality off-the-shelf multilingual retrievers and generators, task-specific prompt engineering is needed to enable generation in user languages. Moreover, current evaluation metrics need adjustments for multilingual setting, to account for variations in spelling named entities. The main limitations to be addressed in future works include frequent code-switching in non-Latin alphabet languages, occasional fluency errors, wrong reading of the provided documents, or irrelevant retrieval. We release the code for the resulting mRAG baseline pipeline at https://github.com/naver/bergen.

cs.CL↗

arXiv2024

SPLATE: Sparse Late Interaction Retrieval

The late interaction paradigm introduced with ColBERT stands out in the neural Information Retrieval space, offering a compelling effectiveness-efficiency trade-off across many benchmarks. Efficient late interaction retrieval is based on an optimized multi-step strategy, where an approximate search first identifies a set of candidate documents to re-rank exactly. In this work, we introduce SPLATE, a simple and lightweight adaptation of the ColBERTv2 model which learns an ``MLM adapter'', mapping its frozen token embeddings to a sparse vocabulary space with a partially learned SPLADE module. This allows us to perform the candidate generation step in late interaction pipelines with traditional sparse retrieval techniques, making it particularly appealing for running ColBERT in CPU environments. Our SPLATE ColBERTv2 pipeline achieves the same effectiveness as the PLAID ColBERTv2 engine by re-ranking 50 documents that can be retrieved under 10ms.

cs.IR↗

arXiv2024

Two-Step SPLADE: Simple, Efficient and Effective Approximation of SPLADE

Learned sparse models such as SPLADE have successfully shown how to incorporate the benefits of state-of-the-art neural information retrieval models into the classical inverted index data structure. Despite their improvements in effectiveness, learned sparse models are not as efficient as classical sparse model such as BM25. The problem has been investigated and addressed by recently developed strategies, such as guided traversal query processing and static pruning, with different degrees of success on in-domain and out-of-domain datasets. In this work, we propose a new query processing strategy for SPLADE based on a two-step cascade. The first step uses a pruned and reweighted version of the SPLADE sparse vectors, and the second step uses the original SPLADE vectors to re-score a sample of documents retrieved in the first stage. Our extensive experiments, performed on 30 different in-domain and out-of-domain datasets, show that our proposed strategy is able to improve mean and tail response times over the original single-stage SPLADE processing by up to $30\times$ and $40\times$, respectively, for in-domain datasets, and by 12x to 25x, for mean response on out-of-domain datasets, while not incurring in statistical significant difference in 60\% of datasets.

cs.IR↗

arXiv2024

A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE

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 Learning datasets and out-of-domain datasets such as BEIR and LoTTE. In the first set of experiments, we show how cross-encoder rerankers are hard to distinguish when it comes to re-rerank SPLADE on MS MARCO. Observations shift in the out-of-domain scenario, where both the type of model and the number of documents to re-rank have an impact on effectiveness. Then, we focus on listwise rerankers based on Large Language Models -- especially GPT-4. While GPT-4 demonstrates impressive (zero-shot) performance, we show that traditional cross-encoders remain very competitive. Overall, our findings aim to to provide a more nuanced perspective on the recent excitement surrounding LLM-based re-rankers -- by positioning them as another factor to consider in balancing effectiveness and efficiency in search systems.

cs.IR↗

arXiv2024

SPLADE-v3: New baselines for SPLADE

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 compare this new version to BM25, SPLADE++, as well as re-rankers, and showcase its effectiveness via a meta-analysis over more than 40 query sets. SPLADE-v3 further pushes the limit of SPLADE models: it is statistically significantly more effective than both BM25 and SPLADE++, while comparing well to cross-encoder re-rankers. Specifically, it gets more than 40 MRR@10 on the MS MARCO dev set, and improves by 2% the out-of-domain results on the BEIR benchmark.

cs.IR↗