213 citations
- Centre National de la Recherche ScientifiqueFR3 papers
- Sorbonne UniversitéFR3 papers
- Tel Aviv UniversityIL3 papers
- University of AntwerpBE3 papers
- Assistance Publique – Hôpitaux de ParisFR2 papers
- InsermFR2 papers
- Institut du CerveauFR2 papers
- Institut national de recherche en sciences et technologies du numériqueFR2 papers
- Laboratoire d’Imagerie BiomédicaleFR2 papers
- New York UniversityUS2 papers
- Université Paris CitéFR2 papers
- Alpha Genesis (United States)US1 paper
18 papers
Beware of "Explanations" of AI
David Martens, Galit Shmueli, Theodoros Evgeniou +14
Understanding the decisions made and actions taken by increasingly complex AI system remains a key challenge. This has led to an expanding field of research in explainable artifici…
Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey
Katerina Korre, Dimitris Tsirmpas, Nikos Gkoumas +5
We present a survey of methods for assessing and enhancing the quality of online discussions, focusing on the potential of LLMs. While online discourses aim, at least in theory, to…
New Additive OCBA Procedures for Robust Ranking and Selection
Yuchen Wan, Zaile Li, L. Jeff Hong
Robust ranking and selection (R&S) is an important and challenging variation of conventional R&S that seeks to select the best alternative among a finite set of alternatives. It ca…
The algebra of binary trees is affine complete
Andre Arnold, Patrick Cegielski, Serge Grigorieff +1
A function on an algebra is congruence preserving if, for any congruence, it maps pairs of congruent elements onto pairs of congruent elements. We show that on the algebra of binar…
Metafeatures-based Rule-Extraction for Classifiers on Behavioral and Textual Data
Yanou Ramon, David Martens, Theodoros Evgeniou +1
Machine learning models on behavioral and textual data can result in highly accurate prediction models, but are often very difficult to interpret. Rule-extraction techniques have b…
Counterfactual Explanation Algorithms for Behavioral and Textual Data
Yanou Ramon, David Martens, Foster Provost +1
We study the interpretability of predictive systems that use high-dimensonal behavioral and textual data. Examples include predicting product interest based on online browsing data…