7 citations · 39 across the 53 of their papers we have counts for
60 papers
UIBK-Embedding: Effective Text Retrieval by Unifying Dense and Late-Interaction Retrieval
Abdelrahman Abdallah, Mohammed Ali, Adam Jatowt
Dense bi-encoders and late-interaction retrievers are usually treated as alternatives, yet they fail on different queries: one vector captures what a text is about, token-level mat…
Precision over Scale: A Polish-Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models
Grzegorz Kulik, Mikołaj Pokrywka, Adam Jatowt +1
Dialectal machine translation remains challenging due to limited data and strong linguistic variation not captured by standard benchmarks, which often assume standardized and well-…
OBLIQ-IR: Training a Dense Retriever for Oblique Queries
Mahmoud Abdalla, Abdelrahman Abdallah, Shaimaa Sedek +1
Oblique retrieval, as exemplified by OBLIQ-Bench, asks a retriever to find documents whose relevance is determined by a latent attribute (an implicit stance, an analogous reasoning…
The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrieval
Jamie Holdcroft, Abdelrahman Abdallah, Adam Jatowt
Many production RAG systems implement retrieval abstention by thresholding raw similarity scores, implicitly treating score magnitude as a confidence signal. We demonstrate that th…
SmallReason-ColBERT: An Ultra-Small Late-Interaction Retriever for Reasoning Intensive Retrieval
Abdelrahman Abdallah, Mohammed Ali, Adam Jatowt
Reasoning-intensive retrieval remains difficult for small models. Compact public ColBERTs are usually trained on general-purpose corpora and underperform reasoning-tuned 150M+ base…
Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs
Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani +2
Multiple-choice questions (MCQs) are a standard format for evaluating large language models (LLMs), yet the popularity of answer options can confound evaluation. Modern LLMs system…
Automating Multi-Hop RAG Evaluation via TRIAD: From Context Extraction to Validated Dataset Generation
Lorenz Brehme, Adam Jatowt
Recent advances in LLMs and the adoption of RAG systems in industry have created a need for domain-specific question-answer datasets that can assess RAG performance on proprietary…
Difficulty-Gated Fusion of Reasoning Views for Temporal Retrieval
Jamie Holdcroft, Abdelrahman Abdallah, Adam Jatowt
Reasoning-intensive temporal retrieval requires matching a query to documents whose relevance depends on shared temporal reasoning rather than lexical overlap. Expanding a query in…
EXCISE: Query-Side Exclusion for Late-Interaction Retrieval
Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt
Late-interaction retrievers handle exclusion queries poorly. When a user asks for X but not Z, the additive MaxSim score promotes documents covering Z, a problem we call exclusion…
MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning
Abdelrahman Abdallah, AbdelRahim A. Elmadany, Sameh Al Natour +3
Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and scales that support them. A s…
Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval
Abdelrahman Abdallah, Mahmoud Abdalla, Mohammed Ali +1
Late-interaction vision-language retrievers represent each document page as many visual token embeddings and score queries with MaxSim. In systems such as ColPali, ColQwen, ColNomi…
Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring
Jamshid Mozafari, Bhawna Piryani, Adam Jatowt
Estimating question difficulty is a critical component in evaluating and improving large language models (LLMs) for question answering (QA). Existing approaches often rely on reada…
Pretraining Exposure Explains Popularity Judgments in Large Language Models
Jamshid Mozafari, Bhawna Piryani, Adam Jatowt
Large language models (LLMs) exhibit systematic preferences for well-known entities, a phenomenon often attributed to popularity bias. However, the extent to which these preference…
Context Convergence Improves Answering Inferential Questions
Jamshid Mozafari, Bhawna Piryani, Adam Jatowt
While Large Language Models (LLMs) are widely used in open-domain Question Answering (QA), their ability to handle inferential questions-where answers must be derived rather than d…
REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction
Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt
Extracting structured, machine-readable compliance criteria from regulatory documents remains an open challenge. Single-pass language models hallucinate structural elements, lose h…
BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination
Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani +1
Reasoning-intensive retrieval requires deep semantic inference beyond surface-level keyword matching, posing a challenge for current LLM-based rerankers limited by context constrai…
Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead
Abdelrahman Abdallah, Jamie Holdcroft, Mohammed Ali +1
Large language model retrievers improve performance on complex queries, but their practical value depends on efficiency, robustness, and reliable confidence signals in addition to…
How often do Answers Change? Estimating Recency Requirements in Question Answering
Bhawna Piryani, Zehra Mert, Adam Jatowt
Large language models (LLMs) often rely on outdated knowledge when answering time-sensitive questions, leading to confident yet incorrect responses. Without explicit signals indica…
Negative Sampling Techniques in Information Retrieval: A Survey
Laurin Wischounig, Abdelrahman Abdallah, Adam Jatowt
Information Retrieval (IR) is fundamental to many modern NLP applications. The rise of dense retrieval (DR), using neural networks to learn semantic vector representations, has sig…
PARSE: An Open-Domain Reasoning Question Answering Benchmark for Persian
Jamshid Mozafari, Seyed Parsa Mousavinasab, Adam Jatowt
Reasoning-focused Question Answering (QA) has advanced rapidly with Large Language Models (LLMs), yet high-quality benchmarks for low-resource languages remain scarce. Persian, spo…
Inferential Question Answering
Jamshid Mozafari, Hamed Zamani, Guido Zuccon +1
Despite extensive research on a wide range of question answering (QA) systems, most existing work focuses on answer containment-i.e., assuming that answers can be directly extracte…
MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrieval
Abdelrahman Abdallah, Mohamed Darwish Mounis, Mahmoud Abdalla +6
Existing retrieval benchmarks primarily consist of text-based queries where keyword or semantic matching is usually sufficient. Many real-world queries contain multimodal elements,…
TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval
Abdelrahman Abdallah, Mohammed Ali, Muhammad Abdul-Mageed +1
Existing temporal QA benchmarks focus on simple fact-seeking queries from news corpora, while reasoning-intensive retrieval benchmarks lack temporal grounding. However, real-world…
RECOR: Reasoning-focused Multi-turn Conversational Retrieval Benchmark
Mohammed Ali, Abdelrahman Abdallah, Amit Agarwal +2
Existing benchmarks treat multi-turn conversation and reasoning-intensive retrieval separately, yet real-world information seeking requires both. To bridge this gap, we present a b…