Retrieval-Augmented Generation improves various aspects of large language models (LLMs) generation, but suffers from computational overhead caused by long contexts, and 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 limited, and do not present 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.

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.

Sparse representation learning based on Pre-trained Language Models has seen a growing interest in Information Retrieval. Such approaches can take advantage of the proven efficiency of inverted indexes and inherit desirable IR priors such as explicit lexical matching or some degree of interpretability. In this work, we thoroughly develop the framework of sparse representation learning in IR, which unifies term weighting and expansion in a supervised setting. We then build on SPLADE—a sparse expansion-based retriever—and show to which extent it is able to benefit from the same training improvements as dense bi-encoders by studying the effect of distillation, hard negative mining, as well as the Pre-trained Language Model’s initialization on itseffectiveness, leading to state-of-the-art results in both in- and out-of-domain evaluation settings (SPLADE++). We furthermore proposeefficiencyimprovements, allowing us to reach latency requirements on par with traditional keyword-based approaches (Efficient-SPLADE).

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, RetroMAE, and LexMAE argue that the MLM task is not sufficient enough to pre-train a transformer network for retrieval and hence propose various tasks to do so. Intrigued by those novel methods, we noticed that all these models used different finetuning protocols, making it hard to assess the benefits of middle training. We propose in this paper a benchmark of CoCondenser, RetroMAE, and LexMAE, under the same finetuning conditions. We compare both dense and sparse approaches under various finetuning protocols and middle training on different collections (MS MARCO, Wikipedia). We use additional middle training baselines, such as a standard MLM finetuning on the retrieval collection, optionally augmented by a CLS predicting the passage term frequency. For the sparse approach, our study reveals that there is almost no statistical difference between those methods: the more effective the finetuning procedure is, the less difference there is between those models. For the dense approach, RetroMAE using MS MARCO as middle-training collection shows excellent results in almost all the settings. Finally, we show that middle training on the retrieval collection, thus adapting the language model to it, is a critical factor. Overall, a better experimental setup should be adopted to evaluate middle training methods.

Neural retrievers based on dense representations combined with Approximate Nearest Neighbors search have recently received a lot of attention, owing their success to distillation and/or better sampling of examples for training -- while still relying on the same backbone architecture. In the meantime, sparse representation learning fueled by traditional inverted indexing techniques has seen a growing interest, inheriting from desirable IR priors such as explicit lexical matching. While some architectural variants have been proposed, a lesser effort has been put in the training of such models. In this work, we build on SPLADE -- a sparse expansion-based retriever -- and show to which extent it is able to benefit from the same training improvements as dense models, by studying the effect of distillation, hard-negative mining as well as the Pre-trained Language Model initialization. We furthermore study the link between effectiveness and efficiency, on in-domain and zero-shot settings, leading to state-of-the-art results in both scenarios for sufficiently expressive models.

In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to work well. Meanwhile, there has been a growing interest in learning sparse representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes. In this work, we present a new first-stage ranker based on explicit sparsity regularization and a log-saturation effect on term weights, leading to highly sparse representations and competitive results with respect to state-of-the-art dense and sparse methods. Our approach is simple, trained end-to-end in a single stage. We also explore the trade-off between effectiveness and efficiency, by controlling the contribution of the sparsity regularization.

We present a Composite Code Sparse Autoencoder (CCSA) approach for Approximate Nearest Neighbor (ANN) search of document representations based on Siamese-BERT models. In Information Retrieval (IR), the ranking pipeline is generally decomposed in two stages: the first stage focuses on retrieving a candidate set from the whole collection. The second stage re-ranks the candidates by relying on more complex models. Recently, Siamese-BERT models have been used as first stage rankers to replace or complement the traditional bag-of-words models. However, indexing and searching a large document collection requires efficient similarity search on dense vectors and this is why ANN techniques come into play. Since composite codes are naturally sparse, we show how CCSA can learn efficient parallel inverted index thanks to an uniformity regularizer. Our experiments on MS MARCO reveal that for the same quantization budget and [email protected] targets, CCSA is able to outperform IVF (inverted-index file) with product quantization on both