EigenLI introduces a spectral approximation framework that compresses late‑interaction representations by identifying document‑specific low‑dimensional subspaces. By selecting dominant eigendirections, it constructs reduced interaction representations that outperform clustering‑based pooling methods on ColBERTv2 and AnswerAI‑ColBERT‑small. The framework also yields EigenLI‑SV, a single‑vector ANN‑compatible representation that consistently surpasses comparable surrogates such as MUVERA across multiple datasets and text models.
arXiv:2605. 30120v3 Announce Type: replace-cross Abstract: Multi-vector retrieval (MVR) models, exemplified by ColBERT, have established new benchmarks in retrieval accuracy by preserving fine-grained token-level interactions.
The paper introduces MARETopic, a training‑free framework that identifies topics by selecting rank‑based prototype documents from pretrained embeddings. By projecting embeddings onto a low‑dimensional manifold and building ranked neighborhood lists, a greedy algorithm picks exactly K exemplar texts whose neighborhoods cover the corpus. Two variants—MARETopic_Corr, which uses a query‑performance predictor and rank correlation, and MARETopic_Diff, which employs a rank‑based diffusion matrix—achieve higher purity and NMI on benchmark datasets and run significantly faster, while also improving topic coherence and vocabulary diversity through a novel Maximal Marginal Relevance step.
The paper introduces two randomized approaches to accelerate spectral co‑clustering of word‑document matrices: one based on randomized SVD via random projection, and another combining partial SVD with element‑wise random sampling. Experiments on real and synthetic data show both methods cut runtime compared to full SVD, with the projection technique offering more consistent performance across varied sparsity levels, while the sampling method excels on denser matrices. The study highlights that the choice of approximation should align with the data’s structural properties.
arXiv:2609.07262v1 Announce Type: cross Abstract: Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage...
arXiv:2608.22980v1 Announce Type: cross Abstract: Dense vector retrieval has become the foundation of modern semantic search, yet existing approximate nearest neighbor (ANN) indexes treat an embeddin...
arXiv:2608. 00065v1 Announce Type: cross Abstract: Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts.
arXiv:2607. 24025v1 Announce Type: cross Abstract: Transformer architectures have achieved remarkable success across diverse domains; however, directly applying their standard self-attention mechanism to recommendation often yields suboptimal performance, sometimes even trailing behind well-designed simple recommendation models.
As retrieval systems scale, high-quality reranking becomes increasingly important. However, most existing rerankers, whether encoder-based or decoder-based, jointly encode the query and passage, tightly coupling their computation and limiting deployment efficiency as well as flexibility.
Multi-vector dense retrieval models, such as ColBERT, achieve strong retrieval effectiveness by modelling fine-grained token-level interactions between queries and documents. Methods such as PLAID use centroid-based quantisation of each token's vector to reduce the index size and speed up retrieval while maintaining strong effectiveness.
arXiv:2608.29001v1 Announce Type: new Abstract: In a data-driven world, efficiently organizing and mapping relationships between objects is crucial. Graphs are powerful tools for modeling these conne...
arXiv:2608. 08704v1 Announce Type: cross Abstract: Kernel spectral clustering with a single bandwidth can be inadequate for data exhibiting multiple characteristic pairwise-distance scales, a problem particularly prevalent in the high-dimensional regime.
arXiv:2606.22807v3 Announce Type: replace Abstract: As retrieval systems scale, effective and efficient reranking becomes increasingly important. However, most existing encoder- and decoder-based rer...