Abdelrahman Abdallah

prof_pic.jpg

Digital Science Center (DiSC)

University of Innsbruck

Innsbruck, Austria

Pronouns: He/Him

Hello. Iโ€™m Abdelrahman Abdallah, a final-year Ph.D. candidate advised by Professor Adam Jatowt at the Digital Science Center (DiSC), Department of Computer Science, University of Innsbruck. Currently, I am a research assistant at DiSC. Previously, I worked as a machine learning engineer at DISCO App in Cairo and at KMG Engineering in Kazakhstan, as a machine learning researcher at Satbayev University and Universitร  Caโ€™ Foscari Venezia, and as a research and teaching assistant at Assiut University in Egypt.

As a researcher in machine learning (ML) and natural language processing (NLP), my work focuses on large language models (LLMs), information retrieval, and question answering. I am particularly interested in how LLMs can be used for document retrieval and reranking, robust QA on noisy or OCR text, and reasoning over temporal information in dynamic collections.

My research interests include:

  • LLM-based Reranking & Information Retrieval
  • Open-domain & Multilingual Question Answering
  • Temporal Reasoning for QA & Retrieval
  • Bias in Large Language Models

Please feel free to contact me via email at abdelrahman.abdallah@uibk.ac.at or abdoelsayed2016@gmail.com.

news

Aug 22, 2026 ๐Ÿ—“๏ธ August 2026 - ๐ŸŽ‰ 10 papers accepted at EMNLP 2026: 9 Main Conference papers and 1 Findings paper.
Aug 13, 2026 August 2026 - Our shared task RETECO: Reasoning-Oriented Retrieval was accepted for SemEval-2027 (GitHub).
Aug 07, 2026 August 2026 - One short paper accepted at CIKM 2026: โ€œDifficulty-Gated Fusion of Reasoning Views for Temporal Retrievalโ€.
May 01, 2026 May 2026 - Two papers accepted: MM-BRIGHT at KDD 2026 and Rankify at ACL 2026 Demo.
Apr 05, 2026 ๐Ÿ—“๏ธ April 2026 โ€“ Three papers accepted at ACL 2026:
First paper (Main),
Second paper (Main), and
Third paper (Findings).
Apr 02, 2026 ๐Ÿ—“๏ธ April 2026 โ€“ Our Paper โ€œAre LLM-Based Retrievers Worth Their Cost?โ€ accepted at SIGIR 2026.
CORE A*
Jan 05, 2026 ๐Ÿ—“๏ธ January 2026 โ€“ Our Negative Sampling Survey paper accepted at EACL 2026.
Acceptance rate: ~20%.
Oct 01, 2025 ๐Ÿ—“๏ธ October 2025 โ€“ One paper accepted at WSDM 2026.
Acceptance rate: ~16%.

selected publications

OBLIQ-IR: Training a Dense Retriever for Oblique Queries

Abdalla M., Abdelrahman A., Sedek S., Jatowt A.
EMNLP 2026 (2026)
Paper and code coming soon.

MEMORA: A Memory-Enhanced Multimodal Committee Reranking Agent for Reasoning-Intensive Retrieval

Mahmoud M., Senussi M. F., Abdalla M., Kasem M. S., Abdelrahman A., Kang H.
EMNLP 2026 (2026)
Paper and code coming soon.

SustainableQA: A Comprehensive Question Answering Dataset for Corporate Sustainability and EU Taxonomy Reporting

Ali M., Abdelrahman A., Jatowt A.
EMNLP 2026 (2026)

TEMPO: Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval

Abdelrahman A., Ali M., Abdul-Mageed M., Jatowt A.
EMNLP 2026 (2026)

Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval

Abdelrahman A., Abdalla M., Ali M., Jatowt A.
EMNLP 2026 (2026)

Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs

Abdelrahman A., Ali M., Piryani B., Abdalla M., Jatowt A.
EMNLP 2026 (2026)
Paper and code coming soon.

SmallReason-ColBERT: An Ultra-Small Late-Interaction Retriever for Reasoning-Intensive Retrieval

Abdelrahman A., Ali M., Jatowt A.
EMNLP 2026 (2026)
Paper and code coming soon.

MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning

Abdelrahman A., Elmadany A. A., Al Natour S., Cavusoglu H., Jatowt A., Abdul-Mageed M.
EMNLP 2026 (2026)

The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrieval

Holdcroft J., Abdelrahman A., Jatowt A.
EMNLP 2026 (2026)
Paper and code coming soon.

REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction

Ali M., Abdelrahman A., Jatowt A.
EMNLP Findings 2026 (2026)

MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrieval

Abdelrahman A., Mounis M. D., Abdalla M., Kasem M. S., Senussi M. F., Mahmoud M., Ali M., Jatowt A., Kang H.
KDD 2026 (2026)

BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination

Abdelrahman A., Ali M., Piryani B., Jatowt A.
ACL 2026 (2026)

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

Abdelrahman A., Piryani B., Mozafari J., Herzinger A., Holdcroft J., Jatowt A.
ACL Demo 2026 (2026)

TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions

Abdelrahman A., Bhawna P., Jonas W., Avishek A., Adam J.
WSDM 2026 (2026)
Acceptance rate: 16%

DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation

Abdelrahman A., Mozafari J., Piryani B., Jatowt A.
EMNLP Findings 2025 (2025)

ComplexTempQA: A Large-Scale Dataset for Complex Temporal Question Answering

Raphael G., Abdelrahman A., Michael F., Adam J.
EMNLP 2025 (2025)

RankArena: A unified platform for evaluation of retrieval, reranking and RAG

Abdelrahman A., Abdalla M., Piryani B., Mozafari J., Ali M., Jatowt A.
CIKM 2025 (2025)