7 papers
Revisiting Text Ranking in Deep Research
Chuan Meng, Litu Ou, Sean MacAvaney +1
Deep research has emerged as an important task that aims to address hard queries that need extensive open-web exploration. To tackle it, most prior work equips large language model…
Reproducing Adaptive Reranking for Reasoning-Intensive IR
Mandeep Rathee, V Venktesh, Sean MacAvaney +1
The classical cascading pipeline of retrieve--rerank suffers from a bounded recall problem, stemming from limitations of the first-stage retriever. Most current approaches address…
SuiteEval: Simplifying Retrieval Benchmarks
Andrew Parry, Debasis Ganguly, Sean MacAvaney
Information retrieval evaluation often suffers from fragmented practices -- varying dataset subsets, aggregation methods, and pipeline configurations -- that undermine reproducibil…
Test-time Corpus Feedback: From Retrieval to RAG
Mandeep Rathee, V Venktesh, Sean MacAvaney +1
Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from exte…
On Precomputation and Caching in Information Retrieval Experiments with Pipeline Architectures
Sean MacAvaney, Craig Macdonald
Modern information retrieval systems often rely on multiple components executed in a pipeline. In a research setting, this can lead to substantial redundant computations (e.g., ret…
Improving Low-Resource Retrieval Effectiveness using Zero-Shot Linguistic Similarity Transfer
Andreas Chari, Sean MacAvaney, Iadh Ounis
Globalisation and colonisation have led the vast majority of the world to use only a fraction of languages, such as English and French, to communicate, excluding many others. This…