AIConfPaper
← Search

Virginie Do

9 accepted papers

2026

Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments

Romain Froger, Amine Benhalloum, Andrey Rusakov, Dheeraj Mekala, Emilien Garreau, Gerard Moreno-Torres Bertran +18
ICLR 2026oral

We introduce **Gaia2**, a benchmark for evaluating large language model agents in realistic, asynchronous environments. Unlike prior static or synchronous evaluations, Gaia2 introduces scenarios where environments evolve independently of agent actions, requiring agents to operate under temporal cons…

Cited by 0Source ↗Scholar ↗
2025

Robust LLM safeguarding via refusal feature adversarial training

Lei Yu, Virginie Do, Karen Hambardzumyan, Nicola Cancedda
ICLR 2025poster

Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of training LLMs robustly. We demonstrate that adversarial attacks sh…

Cited by 9Source ↗PDF ↗Scholar ↗
2023

Contextual bandits with concave rewards, and an application to fair ranking

Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric, Nicolas Usunier
ICLR 2023poster

We consider Contextual Bandits with Concave Rewards (CBCR), a multi-objective bandit problem where the desired trade-off between the rewards is defined by a known concave objective function, and the reward vector depends on an observed stochastic context. We present the first algorithm with provably…

Cited by 4Source ↗PDF ↗Scholar ↗
2023

Online Certification of Preference-Based Fairness for Personalized Recommender Systems (Extended Abstract)

Virginie Do, Sam Corbett-Davies, Jamal Atif, Nicolas Usunier
IJCAI 2023poster

Recommender systems are facing scrutiny because of their growing impact on the opportunities we have access to. Current audits for fairness are limited to coarse-grained parity assessments at the level of sensitive groups. We propose to audit for envy-freeness, a more granular criterion aligned with…

Cited by 0Source ↗PDF ↗Scholar ↗
2022

Online Certification of Preference-Based Fairness for Personalized Recommender Systems

Virginie Do, Sam Corbett-Davies, Jamal Atif, Nicolas Usunier
AAAI 2022technical

Recommender systems are facing scrutiny because of their growing impact on the opportunities we have access to. Current audits for fairness are limited to coarse-grained parity assessments at the level of sensitive groups. We propose to audit for envy-freeness, a more granular criterion aligned with…

Cited by 53Source ↗PDF ↗Scholar ↗
2021

E-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks

Maxime Kayser, Oana-Maria Camburu, Leonard Salewski, Cornelius Emde, Virginie Do, Zeynep Akata +1
ICCV 2021poster

Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. Such models are appealing, because they can provide human-friendly and comprehensive explanations. However, the…

Cited by 111PDF ↗code ↗Scholar ↗
2021

Two-sided fairness in rankings via Lorenz dominance

Virginie Do, Sam Corbett-Davies, Jamal Atif, Nicolas Usunier
NeurIPS 2021poster

We consider the problem of generating rankings that are fair towards both users and item producers in recommender systems. We address both usual recommendation (e.g., of music or movies) and reciprocal recommendation (e.g., dating). Following concepts of distributive justice in welfare economics, ou…

Cited by 60Source ↗PDF ↗Scholar ↗