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

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.

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…

This paper studies the linear decodability of query-document relevance from residual-stream activations in instruction-tuned large language models (LLMs) and compares it with generated relevance judgm…

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

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

This paper proposes a framework for multi-hop retrieval as query-set compatibility scoring, improving retrieval performance and downstream QA task performance.

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

OmniRetrieval introduces a unified framework that handles natural language queries across diverse, heterogeneous knowledge sources (text, relational, graphs) by dispatching source-native queries witho…

The Cologne Information Retrieval group participated in iKAT SCAI 2026 shared task using an agentic conversational search system with query rewriting, retrieval, reranking, answer generation, and clar…

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.

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 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…