LongEval: Longitudinal Evaluation of Model Performance at CLEF 2023

Rabab Alkhalifa, Iman Munire Bilal, Hsubhas Borkakoty, José Camacho-Collados, Romain Deveaud, Alaa El-Ebshihy, Luis Espinosa Anke, Gabriela González Sáez, Petra Galuscáková, Lorraine Goeuriot, Elena Kochkina, Maria Liakata, Daniel Loureiro, Harish Tayyar Madabushi, Philippe Mulhem, Florina Piroi, Martin Popel, Christophe Servan, Arkaitz Zubiaga

Abstract: In this paper, we describe the plans for the first LongEval CLEF 2023 shared task dedicated to evaluating the temporal persistence of Information Retrieval (IR) systems and Text Classifiers. The task is motivated by recent research showing that the performance of these models drops as the test data becomes more distant, with respect to time, from the training data. LongEval differs from traditional shared IR and classification tasks by giving special consideration to evaluating models aiming to mitigate performance drop over time. We envisage that this task will draw attention from the IR community and NLP researchers to the problem of temporal persistence of models, what enables or prevents it, potential solutions and their limitations.