25 citations · 41 across the 21 of their papers we have counts for
3 papers · 1 filter
Robust LLM safeguarding via refusal feature adversarial training
Lei Yu, Virginie Do, Karen Hambardzumyan +1
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 jailb…
Contextual bandits with concave rewards, and an application to fair ranking
Virginie Do, Elvis Dohmatob, Matteo Pirotta +2
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…
Online certification of preference-based fairness for personalized recommender systems
Virginie Do, Sam Corbett-Davies, Jamal Atif +1
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 ass…