no code implementations • 21 May 2024 • Kiarash Golzadeh, Lukasz Golab, Jaroslaw Szlichta
Expert search and team formation systems operate on collaboration networks, with nodes representing individuals, labeled with their skills, and edges denoting collaboration relationships.
no code implementations • 11 May 2024 • Joel Rorseth, Parke Godfrey, Lukasz Golab, Divesh Srivastava, Jaroslaw Szlichta
This paper demonstrates RAGE, an interactive tool for explaining Large Language Models (LLMs) augmented with retrieval capabilities; i. e., able to query external sources and pull relevant information into their input context.
no code implementations • 10 Feb 2023 • Joel Rorseth, Parke Godfrey, Lukasz Golab, Mehdi Kargar, Divesh Srivastava, Jaroslaw Szlichta
Towards better explainability in the field of information retrieval, we present CREDENCE, an interactive tool capable of generating counterfactual explanations for document rankers.
no code implementations • 6 Jan 2021 • Reza Karegar, Parke Godfrey, Lukasz Golab, Mehdi Kargar, Divesh Srivastava, Jaroslaw Szlichta
Order dependencies (ODs) capture relationships between ordered domains of attributes.
Databases
1 code implementation • 17 Aug 2020 • Bahare Askari, Jaroslaw Szlichta, Amirali Salehi-Abari
We introduce joint variational autoencoders (JoVA), an ensemble of two VAEs, in which VAEs jointly learn both user and item representations and collectively reconstruct and predict user preferences.