publications

2026

1. KDD

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

   Abdelrahman Abdallah, Mohamed Darwish Mounis, Mahmoud Abdalla, and 6 more authors

   In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2026

   arXiv
2. ACL Demo

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

   Abdelrahman Abdallah, Bhawna Piryani, Jamshid Mozafari, and 3 more authors

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2026

   arXiv Code
3. ACL

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

   Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani, and 1 more author

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, 2026

   arXiv
4. EACL Findings

   Negative Sampling Techniques in Dense Retrieval: A Survey

   Laurin Wischounig, Abdelrahman Abdallah, and Adam Jatowt

   In Findings of the Association for Computational Linguistics: EACL 2026, 2026

   Laurin Wischounig and Abdelrahman Abdallah contributed equally.
5. ACL

   It’s High Time: A Survey of Temporal Information Retrieval and Question Answering

   Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, and 2 more authors

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, 2026

   arXiv
6. ACL Findings

   RECOR: Reasoning-focused Multi-turn Conversational Retrieval Benchmark

   Mohammed Ali, Abdelrahman Abdallah, Amit Agarwal, and 2 more authors

   In Findings of the Association for Computational Linguistics: ACL 2026, 2026

   arXiv
7. SIGIR

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

   Abdelrahman Abdallah, Jamie Holdcroft, Mohammed Ali, and 1 more author

   In Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2026

   arXiv
8. WSDM

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

   Abdelrahman Abdallah, Bhawna Piryani, Jonas Wallat, and 2 more authors

   In Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, 2026

   arXiv Code

2025

1. CIKM

   Evaluating Robustness of LLMs in Question Answering on Multilingual Noisy OCR Data

   Bhawna Piryani, Jamshid Mozafari, Abdelrahman Abdallah, and 2 more authors

   In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025

   arXiv Code
2. CIKM

   RerankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback

   Abdelrahman Abdallah, Mahmoud Abdalla, Bhawna Piryani, and 3 more authors

   In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025

   arXiv Code
3. EMNLP

   ComplexTempQA: A 100m Dataset for Complex Temporal Question Answering

   Raphael Gruber, Abdelrahman Abdallah, Michael Färber, and 1 more author

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025

   Abs DOI arXiv Code

   We introduce ComplexTempQA,a large-scale dataset consisting of over 100 million question-answer pairs designed to tackle the challenges in temporal question answering. ComplexTempQA significantly surpasses existing benchmarks in scale and scope. Utilizing Wikipedia and Wikidata, the dataset covers questions spanning over two decades and offers an unmatched scale. We introduce a new taxonomy that categorizes questions as \textitattributes, \textitcomparisons, and \textitcounting questions, revolving around events, entities, and time periods, respectively. A standout feature of ComplexTempQA is the high complexity of its questions, which demand reasoning capabilities for answering such as across-time comparison, temporal aggregation, and multi-hop reasoning involving temporal event ordering and entity recognition. Additionally, each question is accompanied by detailed metadata, including specific time scopes, allowing for comprehensive evaluation of temporal reasoning abilities of large language models.

4. EMNLP

   How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models

   Abdelrahman Abdallah, Bhawna Piryani, Jamshid Mozafari, and 2 more authors

   In Findings of the Association for Computational Linguistics: EMNLP 2025, Nov 2025

   Abs DOI arXiv Code

   In this work, we present a systematic and comprehensive empirical evaluation of state-of-the-art reranking methods, encompassing large language model (LLM)-based, lightweight contextual, and zero-shot approaches, with respect to their performance in information retrieval tasks. We evaluate in total 22 methods, including 40 variants (depending on used LLM) across several established benchmarks, including TREC DL19, DL20, and BEIR, as well as a novel dataset designed to test queries unseen by pretrained models. Our primary goal is to determine, through controlled and fair comparisons, whether a performance disparity exists between LLM-based rerankers and their lightweight counterparts, particularly on novel queries, and to elucidate the underlying causes of any observed differences. To disentangle confounding factors, we analyse the effects of training data overlap, model architecture, and computational efficiency on reranking performance. Our findings indicate that while LLM-based rerankers demonstrate superior performance on familiar queries, their generalisation ability to novel queries varies, with lightweight models offering comparable efficiency. We further identify that the novelty of queries significantly impacts reranking effectiveness, highlighting limitations in existing approaches.

5. EMNLP

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

   Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani, and 1 more author

   In Findings of the Association for Computational Linguistics: EMNLP 2025, Nov 2025

   Abs DOI arXiv Code

   Large Language Models (LLMs) have transformed listwise document reranking by enabling global reasoning over candidate sets, yet single models often struggle to balance fine-grained relevance scoring with holistic cross-document analysis. We propose DeepAgentRank (DeAR), an open-source framework that decouples these tasks through a dual-stage approach, achieving superior accuracy and interpretability. In Stage 1, we distill token-level relevance signals from a frozen 13B LLaMA teacher into a compact 3, 8B student model using a hybrid of cross-entropy, RankNet, and KL divergence losses, ensuring robust pointwise scoring. In Stage 2, we attach a second LoRA adapter and fine-tune on 20K GPT-4o-generated chain-of-thought permutations, enabling listwise reasoning with natural-language justifications. Evaluated on TREC-DL19/20, eight BEIR datasets, and NovelEval-2306, DeAR surpasses open-source baselines by +5.1 nDCG@5 on DL20 and achieves 90.97 nDCG@10 on NovelEval, outperforming GPT-4 by +3.09. Without fine-tuning on Wikipedia, DeAR also excels in open-domain QA, achieving 54.29 Top-1 accuracy on Natural Questions, surpassing baselines like MonoT5, UPR, and RankGPT. Ablations confirm that dual-loss distillation ensures stable calibration, making DeAR a highly effective and interpretable solution for modern reranking systems.

6. Medical Physics

   A deep learning framework for accurate mammographic mass classification using local context attention module

   Ibrahim Abdelhalim, Yassir Almalki, Abdelrahman Abdallah, and 8 more authors

   Medical Physics, Nov 2025
7. SIGIR

   Wrong Answers Can Also Be Useful: PlausibleQA-A Large-Scale QA Dataset with Answer Plausibility Scores

   Jamshid Mozafari, Abdelrahman Abdallah, Bhawna Piryani, and 1 more author

   In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Nov 2025

   arXiv Code
8. IEEE Access

   Improving BI-RADS Mammographic Classification With Self-Supervised Vision Transformers and Cascade Learning

   Abdelrahman Abdallah, Mahmoud SalahEldin Kasem, Ibrahim Abdelhalim, and 2 more authors

   IEEE Access, Nov 2025
9. ISBI

   CascadePLS-ViT: Cascade with Patch-Level Self-Supervised Vision Transformers for Breast Cancer Classification in Mammography

   Abdelrahman Abdallah, Mahmoud SalahEldin Kasem, Ibrahim Abdelhalim, and 3 more authors

   In 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), Nov 2025
10. ACL

    A Study into Investigating Temporal Robustness of LLMs

    Jonas Wallat, Abdelrahman Abdallah, Adam Jatowt, and 1 more author

    In Findings of the Association for Computational Linguistics: ACL 2025, Jul 2025

    Abs DOI arXiv Code

    Large Language Models (LLMs) encapsulate a surprising amount of factual world knowledge. However, their performance on temporal questions and historical knowledge is limited because they often cannot understand temporal scope and orientation or neglect the temporal aspect altogether.In this study, we aim to measure precisely how robust LLMs are for question answering based on their ability to process temporal information and perform tasks requiring temporal reasoning and temporal factual knowledge. Specifically, we design eight time-sensitiverobustness tests for factual information to check the sensitivity of six popular LLMs in the zero-shot setting.Overall, we find LLMs lacking temporal robustness, especially to temporal reformulations and the use of different granularities of temporal references. We show how a selection of these eight tests can be used automatically to judge a model’s temporal robustness for user questions on the fly. Finally, we apply the findings of this study to improve the temporal QA performance by up to 55%.

11. NAACL

    ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval

    Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani, and 1 more author

    In Findings of the Association for Computational Linguistics: NAACL 2025, Apr 2025

    Abs DOI

    Retrieval-Augmented Generation (RAG) models have drawn considerable attention in modern open-domain question answering. The effectiveness of RAG depends on the quality of the top retrieved documents. However, conventional retrieval methods sometimes fail to rank the most relevant documents at the top. In this paper, we introduce ASRANK, a new re-ranking method based on scoring retrieved documents using zero-shot answer scent which relies on a pre-trained large language model to compute the likelihood of the document-derived answers aligning with the answer scent. Our approach demonstrates marked improvements across several datasets, including NQ, TriviaQA, WebQA, ArchivalQA, HotpotQA, and Entity Questions. Notably, ASRANK increases Top-1 retrieval accuracy on NQ from 19.2% to 46.5% for MSS and 22.1% to 47.3% for BM25. It also shows strong retrieval performance on several datasets compared to state-of-the-art methods (47.3 Top-1 by ASRANK vs 35.4 by UPR by BM25).

12. COLING

    DynRank: Improve Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification

    Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani, and 2 more authors

    In Proceedings of the 31st International Conference on Computational Linguistics, Jan 2025

    Abs

    This paper presents DynRank, a novel framework for enhancing passage retrieval in open-domain question-answering systems through dynamic zero-shot question classification. Traditional approaches rely on static prompts and pre-defined templates, which may limit model adaptability across different questions and contexts. In contrast, DynRank introduces a dynamic prompting mechanism, leveraging a pre-trained question classification model that categorizes questions into fine-grained types. Based on these classifications, contextually relevant prompts are generated, enabling more effective passage retrieval. We integrate DynRank into existing retrieval frameworks and conduct extensive experiments on multiple QA benchmark datasets.

2024

1. MICCAI

   IHRRB-DINO: Identifying High-Risk Regions of Breast Masses in Mammogram Images Using Data-Driven Instance Noise (DINO)

   Mahmoud SalahEldin Kasem, Abdelrahman Abdallah, Ibrahim Abdelhalim, and 3 more authors

   In International Conference on Medical Image Computing and Computer-Assisted Intervention, Jan 2024
2. EMNLP

   Detecting Temporal Ambiguity in Questions

   Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, and 1 more author

   In Findings of the Association for Computational Linguistics: EMNLP 2024, Nov 2024

   Abs DOI

   Detecting and answering ambiguous questions has been a challenging task in open-domain question answering. Ambiguous questions have different answers depending on their interpretation and can take diverse forms. Temporally ambiguous questions are one of the most common types of such questions. In this paper, we introduce TEMPAMBIQA, a manually annotated temporally ambiguous QA dataset consisting of 8,162 open-domain questions derived from existing datasets. Our annotations focus on capturing temporal ambiguity to study the task of detecting temporally ambiguous questions. We propose a novel approach by using diverse search strategies based on disambiguate versions of the questions. We also introduce and test non-search, competitive baselines for detecting temporal ambiguity using zero-shot and few-shot approaches.

3. EMNLP

   Exploring Hint Generation Approaches for Open-Domain Question Answering

   Jamshid Mozafari, Abdelrahman Abdallah, Bhawna Piryani, and 1 more author

   In Findings of the Association for Computational Linguistics: EMNLP 2024, Nov 2024

   Abs DOI

   Automatic Question Answering (QA) systems rely on contextual information to provide accurate answers. Commonly, contexts are prepared through either retrieval-based or generation-based methods. The former involves retrieving relevant documents from a corpus like Wikipedia, whereas the latter uses generative models such as Large Language Models (LLMs) to generate the context. In this paper, we introduce a novel context preparation approach called HINTQA, which employs Automatic Hint Generation (HG) techniques. Unlike traditional methods, HINTQA prompts LLMs to produce hints about potential answers for the question rather than generating relevant context. We evaluate our approach across three QA datasets including TriviaQA, Natural Questions, and Web Questions, examining how the number and order of hints impact performance. Our findings show that the HINTQA surpasses both retrieval-based and generation-based approaches. We demonstrate that hints enhance the accuracy of answers more than retrieved and generated contexts.

4. SIGIR

   Arabicaqa: A comprehensive dataset for arabic question answering

   Abdelrahman Abdallah, Mahmoud Kasem, Mahmoud Abdalla, and 4 more authors

   In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Nov 2024
5. ACM Comput. Surv.

   Deep Learning for Table Detection and Structure Recognition: A Survey

   Mahmoud Salaheldin Kasem, Abdelrahman Abdallah, Alexander Berendeyev, and 7 more authors

   ACM Comput. Surv., Oct 2024

   Abs DOI

   Tables are everywhere, from scientific journals, articles, websites, and newspapers all the way to items we buy at the supermarket. Detecting them is thus of utmost importance to automatically understanding the content of a document. The performance of table detection has substantially increased thanks to the rapid development of deep learning networks. The goals of this survey are to provide a profound comprehension of the major developments in the field of Table Detection, offer insight into the different methodologies, and provide a systematic taxonomy of the different approaches. Furthermore, we provide an analysis of both classic and new applications in the field. Lastly, the datasets and source code of the existing models are organized to provide the reader with a compass on this vast literature. Finally, we go over the architecture of utilizing various object detection and table structure recognition methods to create an effective and efficient system, as well as a set of development trends to keep up with state-of-the-art algorithms and future research. We have also set up a public GitHub repository where we will be updating the most recent publications, open data, and source code. The GitHub repository is available at https://github.com/abdoelsayed2016/table-detection-structure-recognition.

2023

1. Journal of Big Data

   Exploring the state of the art in legal QA systems

   Abdelrahman Abdallah, Bhawna Piryani, and Adam Jatowt

   Journal of Big Data, Oct 2023