collaborators

14 papers

cs.IR2026

As We May Search

Saber Zerhoudi, Adam Roegiest, Jelena Mitrovic +1

The sensitive information in personal documents, legal files, and medical records is among the most valuable things to search, yet current retrieval-augmented generation systems st…

cs.IR2026

Metadata, Structure, or Strategy? A Decomposition of RAG Context Enrichment

Saber Zerhoudi, Michael Granitzer, Jelena Mitrovic

Retrieval-augmented generation (RAG) systems increasingly enrich retrieved passages by attaching quality metadata, structuring them into explicit records, and adopting multi-hop re…

cs.IR2026

NuggetIndex: Governed Atomic Retrieval for Maintainable RAG

Saber Zerhoudi, Michael Granitzer, Jelena Mitrovic

Retrieval-augmented generation (RAG) systems are frequently evaluated via fact-based metrics, yet standard implementations retrieve passages or static propositions. This unit misma…

cs.IR2026

AgentSim: A Platform for Verifiable Agent-Trace Simulation

Saber Zerhoudi, Michael Granitzer, Jelena Mitrovic

Training trustworthy agentic LLMs requires data that shows the grounded reasoning process, not just the final answer. Existing datasets fall short: question-answering data is outco…

cs.IR2026

IIRSim Studio: A Dashboard for User Simulation

Saber Zerhoudi, Adam Roegiest, Michael Granitzer

User simulation is a valuable methodology for evaluation in Information Retrieval (IR), enabling low-cost experimentation and counterfactual analysis. However, existing simulation…

cs.IR2026

Beyond the Click: A Framework for Inferring Cognitive Traces in Search

Saber Zerhoudi, Michael Granitzer

User simulators are essential for evaluating search systems, but they primarily reproduce user actions without modeling the underlying thought process. Large-scale interaction logs…