This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.

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.

CoHyDE introduces an iterative co-training framework that jointly optimizes an LLM rewriter and a dense encoder, significantly improving tool retrieval accuracy for LLM agents, especially on vague que…

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

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…

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…

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

The paper proposes Dynamic Adapter Routing (DAR), a novel method that significantly improves continual multimodal retrieval by adaptively selecting and merging specialized adapters.

MIRA proposes a novel source-aware filtering framework that discovers and anchors evaluation rubrics during data selection, significantly improving code-oriented mid-training data quality while reduci…

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

The paper proposes BiRD, a bidirectional ranking defense mechanism that enhances the robustness of Retrieval-Augmented Generation (RAG) against adversarial attacks by analyzing the alignment between f…

RASER introduces a family of cheap, router-based systems that selectively decide whether to perform expensive multi-hop retrieval, significantly reducing LLM token costs while maintaining state-of-the…

HiKEY proposes a hierarchical, tree-based multimodal retrieval framework that significantly improves open-domain document question answering by addressing document routing and evidence fragmentation.

The paper introduces SPECTRA, a scalable framework for generating large, synthetic, and controllable information retrieval test collections, demonstrating its ability to expose system scaling and fail…

DynaTree introduces a two-stage framework that pre-constructs a reusable retrieval tree offline using coordinated agents, allowing for efficient, structure-aware, and highly effective time-sensitive n…

The paper introduces a cross-encoder re-ranker trained on attribution scores to improve the retrieval of highly relevant citation passages for legal question answering, outperforming standard semantic…

The paper introduces a Deep Research pipeline that significantly improves literature search recall and demonstrates that human-curated citation lists are often unreliable and do not serve as a true gr…