AJ
Adam Jatowt
cs.CLcs.IRcs.AIcs.LGcs.CVcs.DLcs.SEauditable machine learningClinical pharmacy information systemsContext-aware
On Valency
published · living versionsW_f473fem2·v1 · currentpublished
UIBK-Embedding: Effective Text Retrieval by Unifying Dense and Late-Interaction Retrieval
with Abdelrahman Abdallah, Mohammed Ali
1 version
Preprints & journals
97 papers in the corpus · 2017–2026UIBK-Embedding: Effective Text Retrieval by Unifying Dense and Late-Interaction Retrieval2610.27195v1 · Abdelrahman Abdallah, Mohammed Ali, Adam Jatowt2026 · 0 citationsarXivon Valency
MemRevise: A Self-Revising Memory for Conversational Search2610.24672v1 · Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt2026 · 0 citationsarXiv
Precision over Scale: A Polish-Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models2610.01082v2 · Grzegorz Kulik, Miko\laj Pokrywka, Adam Jatowt et al.2026 · 0 citationsarXiv
OBLIQ-IR: Training a Dense Retriever for Oblique Queries2609.29649v1 · Mahmoud Abdalla, Abdelrahman Abdallah, Shaimaa Sedek et al.2026 · 0 citationsarXiv
The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrieval2609.15578v1 · Jamie Holdcroft, Abdelrahman Abdallah, Adam Jatowt2026 · 0 citationsarXiv
Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking2609.07379v2 · Tien Nam Nguyen, Emanuela Boros, Ahmed Hamdi et al.2026 · 0 citationsarXiv
Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs2608.29257v1 · Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani et al.2026 · 0 citationsarXiv
SmallReason-ColBERT: An Ultra-Small Late-Interaction Retriever for Reasoning Intensive Retrieval2609.29652v1 · Abdelrahman Abdallah, Mohammed Ali, Adam Jatowt2026 · 0 citationsarXiv
Automating Multi-Hop RAG Evaluation via TRIAD: From Context Extraction to Validated Dataset Generation2608.21558v1 · Lorenz Brehme, Adam Jatowt2026 · 0 citationsarXiv
Difficulty-Gated Fusion of Reasoning Views for Temporal Retrieval2608.08940v1 · Jamie Holdcroft, Abdelrahman Abdallah, Adam Jatowt2026 · 0 citationsarXiv
EXCISE: Query-Side Exclusion for Late-Interaction Retrieval2608.05497v1 · Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt2026 · 0 citationsarXiv
MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning2606.11537v2 · Abdelrahman Abdallah, AbdelRahim A. Elmadany, Sameh Al Natour et al.2026 · 0 citationsarXiv
Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval2606.04300v1 · Abdelrahman Abdallah, Mahmoud Abdalla, Mohammed Ali et al.2026 · 0 citationsarXiv
Context Convergence Improves Answering Inferential Questions2605.12370v1 · Jamshid Mozafari, Bhawna Piryani, Adam Jatowt2026 · 0 citationsProceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2026)
Pretraining Exposure Explains Popularity Judgments in Large Language Models2605.12382v1 · Jamshid Mozafari, Bhawna Piryani, Adam Jatowt2026 · 0 citationsProceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2026)
Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring2605.12398v1 · Jamshid Mozafari, Bhawna Piryani, Adam Jatowt2026 · 0 citationsProceedings of the 64rd Annual Meeting of the Association for Computational Linguistics (ACL 2026)
REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction2604.12054v2 · Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt2026 · 0 citationsarXiv
BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination2604.08834v1 · Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani et al.2026 · 0 citationsarXiv
Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead2604.03676v1 · Abdelrahman Abdallah, Jamie Holdcroft, Mohammed Ali et al.2026 · 0 citationsarXiv
Event-Centric Human Value Understanding in News-Domain Texts: An Actor-Conditioned, Multi-Granularity Benchmark2603.17838v1 · Yao Wang, Xin Liu, Zhuochen Liu et al.2026 · 0 citationsarXiv
How often do Answers Change? Estimating Recency Requirements in Question Answering2603.16544v1 · Bhawna Piryani, Zehra Mert, Adam Jatowt2026 · 0 citationsarXiv
Inferential Question Answering2602.01239v1 · Jamshid Mozafari, Hamed Zamani, Guido Zuccon et al.2026 · 0 citationsarXiv
PARSE: An Open-Domain Reasoning Question Answering Benchmark for Persian2602.01246v1 · Jamshid Mozafari, Seyed Parsa Mousavinasab, Adam Jatowt2026 · 0 citationsarXiv
TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval2601.09523v1 · Abdelrahman Abdallah, Mohammed Ali, Muhammad Abdul-Mageed et al.2026 · 0 citationsarXiv
MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrieval2601.09562v3 · Abdelrahman Abdallah, Mohamed Darwish Mounis, Mahmoud Abdalla et al.2026 · 0 citationsarXiv
RECOR: Reasoning-focused Multi-turn Conversational Retrieval Benchmark2601.05461v1 · Mohammed Ali, Abdelrahman Abdallah, Amit Agarwal et al.2026 · 0 citationsarXiv
Negative Sampling Techniques in Information Retrieval: A Survey2603.18005v1 · Laurin Wischounig, Abdelrahman Abdallah, Adam Jatowt2026 · 0 citationsarXiv
Knowledge-guided graph fusion of mRNA profiles for interpretable cancer subtyping.42822857 · Ni, Jie, Zhang, Xinting, Li, Mingyang et al.2026 · 0 citationsBriefings in functional genomics. 2026;25
Automated Analysis of Sustainability Reports: Using Large Language Models for the Extraction and Prediction of EU Taxonomy-Compliant KPIs2512.24289v1 · Jonathan Schmoll, Adam Jatowt2025 · 0 citationsarXiv
Exploring NLP Benchmarks in an Extremely Low-Resource Setting2509.03962v1 · Ulin Nuha, Adam Jatowt2025 · 0 citationsarXiv
ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation2508.17234v2 · Siying Zhou, Yiquan Wu, Hui Chen et al.2025 · 0 citationsarXiv
DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation2508.16998v1 · Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani et al.2025 · 4 citationsarXiv
How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models2508.16757v1 · Abdelrahman Abdallah, Bhawna Piryani, Jamshid Mozafari et al.2025 · 8 citationsarXiv
RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback2508.05512v1 · Abdelrahman Abdallah, Mahmoud Abdalla, Bhawna Piryani et al.2025 · 0 citationsarXiv
SustainableQA: A Comprehensive Question Answering Dataset for Corporate Sustainability and EU Taxonomy Reporting2508.03000v3 · Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt2025 · 0 citationsarXiv
Evaluating List Construction and Temporal Understanding capabilities of Large Language Models2506.21783v1 · Alexandru Dumitru, V Venktesh, Adam Jatowt et al.2025 · 3 citationsarXiv
Guess the Age of Photos: An Interactive Web Platform for Historical Image Age Estimation2505.22031v1 · Hasan Yucedag, Adam Jatowt2025 · 0 citationsarXiv
It's High Time: A Survey of Temporal Question Answering2505.20243v4 · Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari et al.2025 · 2 citationsProceedings of the 64th Annual Meeting of the Association for Computational Linguistics: ACL 2026
The Impact of International Collaborations with Highly Publishing Countries in Computer Science2505.09776v1 · Alberto Gomez Espes, Michael Faerber, Adam Jatowt2025 · 0 citationsarXiv
Evaluating a customised large language model (DELSTAR) and its ability to address medication-related questions associated with delirium: a quantitative exploratory study.40208398 · Spagl, Katharina Teresa, Watson, Edward William, Jatowt, Adam et al.2025 · 7 citationsInternational journal of clinical pharmacy. 2025;47(4):1053-1063
A Study into Investigating Temporal Robustness of LLMs2503.17073v1 · Jonas Wallat, Abdelrahman Abdallah, Adam Jatowt et al.2025 · 19 citationsarXiv
Evaluating Answer Reranking Strategies in Time-sensitive Question Answering2503.04972v1 · Mehmet Kardan, Bhawna Piryani, Adam Jatowt2025 · 0 citationsarXiv
TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions2502.21024v2 · Abdelrahman Abdallah, Bhawna Piryani, Jonas Wallat et al.2025 · 2 citationsarXiv
From Retrieval to Generation: Comparing Different Approaches2502.20245v1 · Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani et al.2025 · 0 citationsarXiv
Evaluating Robustness of LLMs in Question Answering on Multilingual Noisy OCR Data2502.16781v3 · Bhawna Piryani, Jamshid Mozafari, Abdelrahman Abdallah et al.2025 · 3 citationsarXiv
Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores2502.16358v2 · Jamshid Mozafari, Abdelrahman Abdallah, Bhawna Piryani et al.2025 · 1 citationProceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2025)
Detecting Future-related Contexts of Entity Mentions2502.15332v1 · Puneet Prashar, Krishna Mohan Shukla, Adam Jatowt2025 · 1 citationarXiv
Wisdom of the Crowds in Forecasting: Forecast Summarization for Supporting Future Event Prediction2502.08205v1 · Anisha Saha, Adam Jatowt2025 · 0 citationsarXiv
Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation2502.02464v3 · Abdelrahman Abdallah, Bhawna Piryani, Jamshid Mozafari et al.2025 · 2 citationsarXiv
HintEval: An Open-Source Python Toolkit for Hint Generation and Hint Evaluation2502.00857v2 · Jamshid Mozafari, Bhawna Piryani, Abdelrahman Abdallah et al.2025 · 3 citationsarXiv
Career total: 552 works. 97 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.