4 papers
The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization
Benoit Dherin, Michael Munn, Xavier Gonzalvo +14
Context tokens in a transformer-based language model can be absorbed into the model's weights as a multiplicative operator. We study this operator in the setting of safety instruct…
Looking for Fairness in Recommender Systems
Cécile Logé
Recommender systems can be found everywhere today, shaping our everyday experience whenever we're consuming content, ordering food, buying groceries online, or even just reading th…
Truth Sleuth and Trend Bender: AI Agents to fact-check YouTube videos and influence opinions
Cécile Logé, Rehan Ghori
Misinformation poses a significant threat in today's digital world, often spreading rapidly through platforms like YouTube. This paper introduces a novel approach to combating misi…
Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management
Cécile Logé, Emily Ross, David Yaw Amoah Dadey +4
Recent advances in Natural Language Processing (NLP), and specifically automated Question Answering (QA) systems, have demonstrated both impressive linguistic fluency and a pernici…