25 citations · 60 across the 27 of their papers we have counts for
9 papers · 1 filter
Training on the Test Model: Contamination in Ranking Distillation
Vishakha Suresh Kalal, Andrew Parry, Sean MacAvaney
Neural approaches to ranking based on pre-trained language models are highly effective in ad-hoc search. However, the computational expense of these models can limit their applicat…
Top-Down Partitioning for Efficient List-Wise Ranking
Andrew Parry, Sean MacAvaney, Debasis Ganguly
Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarge…
On the Evaluation of Machine-Generated Reports
James Mayfield, Eugene Yang, Dawn Lawrie +10
Large Language Models (LLMs) have enabled new ways to satisfy information needs. Although great strides have been made in applying them to settings like document ranking and short-…
Generative Relevance Feedback and Convergence of Adaptive Re-Ranking: University of Glasgow Terrier Team at TREC DL 2023
Andrew Parry, Thomas Jaenich, Sean MacAvaney +1
This paper describes our participation in the TREC 2023 Deep Learning Track. We submitted runs that apply generative relevance feedback from a large language model in both a zero-s…
Exploiting Positional Bias for Query-Agnostic Generative Content in Search
Andrew Parry, Sean MacAvaney, Debasis Ganguly
In recent years, neural ranking models (NRMs) have been shown to substantially outperform their lexical counterparts in text retrieval. In traditional search pipelines, a combinati…
A Reproducibility Study of PLAID
Sean MacAvaney, Nicola Tonellotto
The PLAID (Performance-optimized Late Interaction Driver) algorithm for ColBERTv2 uses clustered term representations to retrieve and progressively prune documents for final (exact…
Overview of the TREC 2023 NeuCLIR Track
Dawn Lawrie, Sean MacAvaney, James Mayfield +4
The principal goal of the TREC Neural Cross-Language Information Retrieval (NeuCLIR) track is to study the impact of neural approaches to cross-language information retrieval. The…
Analyzing Adversarial Attacks on Sequence-to-Sequence Relevance Models
Andrew Parry, Maik Fröbe, Sean MacAvaney +2
Modern sequence-to-sequence relevance models like monoT5 can effectively capture complex textual interactions between queries and documents through cross-encoding. However, the use…
FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
Orion Weller, Benjamin Chang, Sean MacAvaney +5
Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models us…