Paper List

Pantaleon Fassbender

As Large Language Models (LLMs) are increasingly deployed in autonomous, high-stakes environments, the fragility of current Reinforcement Learning from Human Feedback (RLHF) alignment protocols remain...

Yair Oppenheim

This paper introduces an empirical extension of the Deep Personal Privacy (DPP) framework, a novel paradigm that reconceptualizes privacy as resistance to inference rather than mere control over data ...

Gaith Rjoub, Jamal Bentahar, Shahed Almobydeen, Ayoub Alsarhan

The large-scale deployment of Large Language Models (LLMs) is constrained by significant energy consumption and operational costs, with inference accounting for up to 90% of the total energy footprint...

Ylenia D'elia, Nicole Caballa, Caitlin Nguyen, Xuege Tong, Akila Kadambi, Lisa Aziz-Zadeh

Large language model (LLM)-based chatbots are increasingly integrated into various sectors of people's lives, including education, healthcare, and retail. As they become more ubiquitous, safety concer...

Jiaee Cheong, Diana S. Chen, William Leung, Cody Chou, Cheryl M. Corcoran, Sinead Kelly, Carrie E. Bearden, Guillermo Cecchi, Justin T. Baker, John M. Kane, Scott W. Woods, Martha E. Shenton, Barnaby Nelson, John Torous

Large language models (LLMs) are increasingly deployed to assess, diagnose, and predict clinical symptoms and outcomes from textual data. However, prior work has shown that LLMs are susceptible to hal...