14 papers
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…
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…
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…
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…
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…
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…