The definition and measurement of information is fundamental to methods for information retrieval, text mining, and machine learning.
A local small-model system for interpretable analysis of library survey data while keeping sensitive institutional data under local control.
A diagnostic HotpotQA study of how retrieval granularity shapes evidence recovery, answer quality, context budgets, and resource use for small-model RAG.
An invited talk on open search, personal AI, and distributed approaches to information discovery.
Decentralized search and retrieval on the web scale. Efficiency, effectiveness, and scalability.
We study decentralized searches in large-scale information networks and discover the phenomenon of Clustering Paradox, that is, how distributed system interconnect and cluster imposes a limit on search performance and scalability.