Dimension d = O(m^{-2} log n) nearly achieves the optimal margin m^rd(+∞, A) for retrieval embeddings, with matching lower bounds showing d = O(k log(n/k)) suffices and is necessary for m = Θ(k^{-1/2}) on k-sparse query matrices.
Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is background (56%).
32
Pith papers citing it
Background
56% of classified citations
citation-role summary
background 5
baseline 2
method 2
citation-polarity summary
representative citing papers
MaxSim similarity can exactly replicate inner products of non-negative sparse vectors of arbitrary dimension, and a proposed Signed MaxSim extension enables exact replication for arbitrary real-valued vectors.
Introduces P-CHR AUC and CRR metrics to demonstrate that semantic caching model selection is limited by calibration quality rather than ranking performance.
DICE aggregates independently encoded document chunks into a single vector to reduce evidence dilution in long-document dense retrieval, reporting gains on LongEmbed especially beyond 4k tokens.
Different scoring mechanisms cause encoder-based authorship attribution models to consolidate authorship signals at different layers, as shown by causal interventions and gradient analysis.
MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
NumColBERT improves ColBERT performance on numerical query conditions non-intrusively via gating and contrastive learning, outperforming fine-tuning while matching or exceeding separate text-number scoring methods.
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
A single model unifies retrieval and context compression for on-device RAG via shared representations, matching traditional RAG performance at 1/10 context size with no extra storage.
In multimodal KB-VQA, gold evidence at the first prompt slot beats gold at the last by 16–26 points, flipping the classic U-shaped lost-in-the-middle pattern into primacy bias.
PlanRAG models natural language exploratory reasoning problems as logical query trees, optimizes them via dynamic programming with a multi-dimensional cost model, and executes iterative retrieval-generation over the trees to outperform prior RAG methods on a new dataset.
LightSTAR achieves state-of-the-art accuracy in visual document retrieval by decomposing the task into LLM-free high-recall candidate selection and vision-adaptive semantic refinement on candidates, cutting end-to-end latency several-fold.
RSRank learns calibrated relevance scores from alignment between representational shifts induced by candidate documents and those from oracle document sets, enabling zero-threshold filtering.
Test-time LLM feedback refines query embeddings to deliver up to 25% relative gains on zero-shot literature search, intent detection, and related benchmarks.
Agentic program search over a frozen encoder API yields retrieval programs that improve nDCG@10 on held-out tasks and unseen encoder families with no per-domain training.
Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.
KAHM yields a compute-efficient query encoder that outperforms matched learned adapters in reconstructing a frozen Mixedbread embedding space on an Austrian-law retrieval task while delivering an 8.53x CPU speedup.
XTR training does not improve retrieval effectiveness over ColBERT but enhances IVF engine efficiency by flattening token scores to produce more discriminative centroids.
A survey that categorizes RIR benchmarks by domain and modality, proposes a taxonomy for integrating reasoning into retrieval pipelines, and outlines key challenges.
ClusterRAG applies density-based clustering to user profiles for collaborative retrieval in personalized RAG and reports best performance on LaMP tasks by combining target and similar-user profiles.
Entity-oriented rerankers show large gains in conditional evaluation but not open-world evaluation on Robust04; the paper attributes this to a coverage–discrimination tradeoff in the entity channel, not to model architecture.
A Voronoi cell estimation framework in embedding space enables principled token pruning for late-interaction models, reducing index size while retaining retrieval quality.
Introduces a reproducible benchmark and hybrid sparse-dense retrieval framework for evidence-grounded access to silicon detector literature, reporting Hit@5 of 0.917 on core queries.
A new joint spatio-temporal enlargement model for micro-video popularity prediction using frame scoring for long sequences and a topology-aware memory bank for unbounded historical associations.
citing papers explorer
-
Retrieval from Within: An Intrinsic Capability of Attention-Based Models
Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.
-
Text Embeddings by Weakly-Supervised Contrastive Pre-training
E5 text embeddings trained with weakly-supervised contrastive pre-training on CCPairs outperform BM25 on BEIR zero-shot and achieve top results on MTEB, beating much larger models.