Maxime DARRIN — accepted AI-conference papers

2025

Learning Task-Agnostic Representations through Multi-Teacher Distillation

Philippe Formont, Maxime DARRIN, Banafsheh Karimian, Eric Granger, Jackie CK Cheung, Ismail Ben Ayed +2

NeurIPS 2025poster

Casting complex inputs into tractable representations is a critical step across various fields. Diverse embedding models emerge from differences in architectures, loss functions, input modalities and datasets, each capturing unique aspects of the input. Multi-teacher distillation leverages this dive…

Cited by 0 Source ↗Scholar ↗

2025

Statistical Deficiency for Task Inclusion Estimation

Loïc Fosse, Frederic Bechet, Benoit Favre, Géraldine Damnati, Gwénolé Lecorvé, Maxime Darrin +2

ACL 2025long

Tasks are central in machine learning, as they are the most natural objects to assess the capabilities of current models. The trend is to build general models able to address any task. Even though transfer learning and multitask learning try to leverage the underlying task space, no well-founded too…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

COSMIC: Mutual Information for Task-Agnostic Summarization Evaluation

Maxime Darrin, Philippe Formont, Jackie Cheung, Pablo Piantanida

ACL 2024long

Assessing the quality of summarizers poses significant challenges—gold summaries are hard to obtain and their suitability depends on the use context of the summarization system. Who is the user of the system, and what do they intend to do with the summary? In response, we propose a novel task-orient…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews

Maxime Darrin, Ines Arous, Pablo Piantanida, Jackie Cheung

ACL 2024long

Scientific peer review is essential for the quality of academic publications. However, the increasing number of paper submissions to conferences has strained the reviewing process. This surge poses a burden on area chairs who have to carefully read an ever-growing volume of reviews and discern each…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

Unsupervised Layer-Wise Score Aggregation for Textual OOD Detection

Maxime Darrin, Guillaume Staerman, Eduardo Dadalto Camara Gomes, Jackie C. K. Cheung, Pablo Piantanida, Pierre Colombo

AAAI 2024technical

Out-of-distribution (OOD) detection is a rapidly growing field due to new robustness and security requirements driven by an increased number of AI-based systems. Existing OOD textual detectors often rely on anomaly scores (\textit{e.g.}, Mahalanobis distance) computed on the embedding output of the…

Cited by 41 Source ↗PDF ↗code ↗Scholar ↗

2024

When is an Embedding Model More Promising than Another?

Maxime DARRIN, Philippe Formont, Ismail Ben Ayed, Jackie CK Cheung, Pablo Piantanida

NeurIPS 2024poster

Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to perform various downstream tasks. The evaluation of embedding models typically depends on domain-specific empirical approaches utilizing downstream tasks, primar…

Cited by 1 Source ↗PDF ↗Scholar ↗

2023

RainProof: An Umbrella to Shield Text Generator from Out-Of-Distribution Data

Maxime DARRIN, Pablo Piantanida, Pierre Colombo

EMNLP 2023long main

Implementing effective control mechanisms to ensure the proper functioning and security of deployed NLP models, from translation to chatbots, is essential. A key ingredient to ensure safe system behaviour is Out-Of-Distribution (OOD) detection, which aims to detect whether an input sample is statist…

Cited by 0 Source ↗Scholar ↗