Research

Research & Publications

My research sits at the intersection of information retrieval, machine learning, and applied mathematics, spanning both empirical systems work and more theoretical problems.

Publications

SIGIR 2026 Main Conference

Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead

Abdelrahman Abdallah, Jamie Holdcroft, Mohammed Ali, Adam Jatowt — Proceedings of the 49th International ACM SIGIR Conference.

Paper PDF

ACL 2026 System Demonstrations

Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation

Abdelrahman Abdallah, Jamie Holdcroft, Adam Jatowt, et al. — Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics.

Paper PDF

CIKM 2026 Accepted to CIKM Main

Difficulty-Gated Fusion of Reasoning Views for Temporal Retrieval

Jamie Holdcroft, Abdelrahman Abdallah, Adam Jatowt — Accepted to The 35th ACM International Conference on Information and Knowledge Management (CIKM).

Paper PDF

EMNLP 2026 Accepted to EMNLP Main

The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrieval

Jamie Holdcroft, Abdelrahman Abdallah, Adam Jatowt — Accepted to The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP).

Paper PDF

In Preparation 2026

Self-Referential Forward-Start Options

Jamie Holdcroft, Jeff Dewynne, Sam Howison — First-author theoretical paper with University of Oxford faculty.

Paper

Current Work

University of Oxford

Self-Referential Forward-Start Options

First author of a theoretical paper on pricing self-referential forward-start options — deriving and analysing the implicit strike equation, and proving unimodality via perturbation-based analysis.

Mathematical Finance Applied Maths

UNSW CSE

Casual Academic

Leading weekly undergraduate laboratory classes in C programming, on recommendation from lecturer and head academic staff.

Teaching Computer Science