Related papers: Spike Hijacking in Late-Interaction Retrieval
With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…
Sparse retrieval methods like BM25 are based on lexical overlap, focusing on the surface form of the terms that appear in the query and the document. The use of inverted indices in these methods leads to high retrieval efficiency. On the…
This paper introduces Sparsified Late Interaction for Multi-vector (SLIM) retrieval with inverted indexes. Multi-vector retrieval methods have demonstrated their effectiveness on various retrieval datasets, and among them, ColBERT is the…
Multi-vector late-interaction retrievers such as ColBERT achieve state-of-the-art retrieval quality, but their query-time cost is dominated by exhaustively computing token-level MaxSim interactions for every candidate document. While…
Dense retrieval compresses texts into single embeddings ranked by cosine similarity. While efficient for recall, this interface is brittle for identity-level matching: minimal compositional edits (negation, role swaps) flip meaning yet…
Late-interaction retrieval (ColBERT, ColPali) scores a query against a document with the MaxSim operator: for every query token, the maximum similarity over the document tokens, summed over query tokens. The standard implementation…
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…
Multi-vector visual retrievers (e.g., ColPali-style late interaction models) deliver strong accuracy, but scale poorly because each page yields thousands of vectors, making indexing and search increasingly expensive. We present Visual RAG…
Modern retrieval systems do not rely on a single ranking model to construct their rankings. Instead, they generally take a cascading approach where a sequence of ranking models are applied in multiple re-ranking stages. Thereby, they…
Recent studies show that BM25-driven dynamic index skipping can greatly accelerate MaxScore-based document retrieval based on the learned sparse representation derived by DeepImpact. This paper investigates the effectiveness of such a…
Images captured nowadays are of varying dimensions with smartphones and DSLR's allowing users to choose from a list of available image resolutions. It is therefore imperative for forensic algorithms such as resampling detection to scale…
In the context of Extreme Multi-label Text Classification (XMTC), where labels are assigned to text instances from a large label space, the long-tail distribution of labels presents a significant challenge. Labels can be broadly categorized…
Pooling-based recurrent neural architectures consistently outperform their counterparts without pooling. However, the reasons for their enhanced performance are largely unexamined. In this work, we examine three commonly used pooling…
[Abridged] - Spectral Retrieval is a plug-in re-ranking stage that interpolates between per-token MaxSim and mean-pool retrieval through a multi-scale sinc convolution over token embeddings. In standard dense retrieval each document is one…
Compared to traditional image retrieval tasks, product retrieval in retail settings is even more challenging. Products of the same type from different brands may have highly similar visual appearances, and the query image may be taken from…
A lot of recent work has focused on sparse learned indexes that use deep neural architectures to significantly improve retrieval quality while keeping the efficiency benefits of the inverted index. While such sparse learned structures…
This paper revisits cluster-based retrieval that partitions the inverted index into multiple groups and skips the index partially at cluster and document levels during online inference using a learned sparse representation. It proposes an…
Learned sparse document representations using a transformer-based neural model has been found to be attractive in both relevance effectiveness and time efficiency. This paper describes a representation sparsification scheme based on hard…
In neural Information Retrieval (IR), 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…
Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…