19 citations · 62 across the 15 of their papers we have counts for
16 papers
Robust Detection of Synthetic Tabular Data under Schema Variability
G. Charbel N. Kindji, Elisa Fromont, Lina Maria Rojas-Barahona +1
The rise of powerful generative models has sparked concerns over data authenticity. While detection methods have been extensively developed for images and text, the case of tabular…
Datum-wise Transformer for Synthetic Tabular Data Detection in the Wild
G. Charbel N. Kindji, Elisa Fromont, Lina Maria Rojas-Barahona +1
The growing power of generative models raises major concerns about the authenticity of published content. To address this problem, several synthetic content detection methods have…
Synthetic Tabular Data Detection In the Wild
G. Charbel N. Kindji, Elisa Fromont, Lina Maria Rojas-Barahona +1
Detecting synthetic tabular data is essential to prevent the distribution of false or manipulated datasets that could compromise data-driven decision-making. This study explores wh…
Cross-table Synthetic Tabular Data Detection
G. Charbel N. Kindji, Lina Maria Rojas-Barahona, Elisa Fromont +1
Detecting synthetic tabular data is essential to prevent the distribution of false or manipulated datasets that could compromise data-driven decision-making. This study explores wh…
Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectors
Ying Zhou, Ben He, Le Sun
With the launch of ChatGPT, large language models (LLMs) have attracted global attention. In the realm of article writing, LLMs have witnessed extensive utilization, giving rise to…
Tabular Data Generation Models: An In-Depth Survey and Performance Benchmarks with Extensive Tuning
G. Charbel N. Kindji, Lina Maria Rojas-Barahona, Elisa Fromont +1
The ability to train generative models that produce realistic, safe and useful tabular data is essential for data privacy, imputation, oversampling, explainability or simulation. H…
Few-Shot Structured Policy Learning for Multi-Domain and Multi-Task Dialogues
Thibault Cordier, Tanguy Urvoy, Fabrice Lefevre +1
Reinforcement learning has been widely adopted to model dialogue managers in task-oriented dialogues. However, the user simulator provided by state-of-the-art dialogue frameworks a…
Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues
Thibault Cordier, Tanguy Urvoy, Fabrice Lefèvre +1
Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. T…
Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers
Sebastien Montella, Betty Fabre, Tanguy Urvoy +2
The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficien…
Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation
Thibault Cordier, Tanguy Urvoy, Lina M. Rojas-Barahona +1
A learning dialogue agent can infer its behaviour from interactions with the users. These interactions can be taken from either human-to-human or human-machine conversations. Howev…
Budgeted Reinforcement Learning in Continuous State Space
Nicolas Carrara, Edouard Leurent, Romain Laroche +3
A Budgeted Markov Decision Process (BMDP) is an extension of a Markov Decision Process to critical applications requiring safety constraints. It relies on a notion of risk implemen…
Corrupt Bandits for Preserving Local Privacy
Pratik Gajane, Tanguy Urvoy, Emilie Kaufmann
We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preservation in online recommender…
Bandit Structured Prediction for Learning from Partial Feedback in Statistical Machine Translation
Artem Sokolov, Stefan Riezler, Tanguy Urvoy
We present an approach to structured prediction from bandit feedback, called Bandit Structured Prediction, where only the value of a task loss function at a single predicted point,…
A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits
Pratik Gajane, Tanguy Urvoy, Fabrice Clérot
We study the K-armed dueling bandit problem which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the se…
Utility-based Dueling Bandits as a Partial Monitoring Game
Pratik Gajane, Tanguy Urvoy
Partial monitoring is a generic framework for sequential decision-making with incomplete feedback. It encompasses a wide class of problems such as dueling bandits, learning with ex…
Random Forest for the Contextual Bandit Problem - extended version
Raphaël Féraud, Robin Allesiardo, Tanguy Urvoy +1
To address the contextual bandit problem, we propose an online random forest algorithm. The analysis of the proposed algorithm is based on the sample complexity needed to find the…