This paper introduces PLAID-PRF, a method for performing Pseudo-Relevance Feedback (PRF) over PLAID, a centroid-based dense retrieval model, to improve retrieval effectiveness.

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative ex…

The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring s…

The paper introduces Single-stage Sparse Retrieval (SSR), a method that replaces computationally expensive vector clustering with sparse autoencoding to achieve highly efficient multi-vector retrieval…

This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.

This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.

The paper proposes an extended version of Hypencoder, a retrieval approach that encodes queries as shallow neural networks, achieving comparable effectiveness with fewer active parameters and higher s…

The paper introduces ADORE, an iterative framework for query expansion using LLMs, which turns retrieval outcomes into feedback for the next expansion.

Xetrieval introduces an embedding-level framework to mechanistically explain dense retrieval decisions by decomposing high-dimensional embeddings into sparse, human-interpretable features.

This paper introduces ScoreGate, a method for controlling retrieval cardinality at inference time using existing scores, reducing over-retrieval and under-retrieval.

The paper presents CoRe, a query rewriter system that uses the deployed multimodal relevance model as its source for reward and closes the simulation-production gap, allowing for weekly redeployment.

The paper proposes formulating RAG design as an architecture search problem and introduces RAISE, a comprehensive framework and benchmark for systematically optimizing RAG hyperparameters.

This paper proves that single-vector embeddings require a larger representation size than multi-vector embeddings to approximate certain similarities.

The paper proposes DINOSAUR, a framework that incorporates embedding uncertainty into Approximate Nearest Neighbour search to improve retrieval for niche, long-tail content.

SkillPager is a novel two-stage framework that efficiently selects minimal, execution-sufficient context from large procedural skill documents by leveraging typed semantic nodes, significantly reducin…