Towards optimizing human-centric objectives in ai-assisted decision-making with offline reinforcement learning

Z Buçinca, S Swaroop, AE Paluch, SA Murphy… - arxiv preprint arxiv …, 2024 - arxiv.org
Imagine if AI decision-support tools not only complemented our ability to make accurate
decisions, but also improved our skills, boosted collaboration, and elevated the joy we …

" Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction

S Zhang, L Ye, X Yi, J Tang, B Shui, H **ng… - arxiv preprint arxiv …, 2024 - arxiv.org
Memories, encompassing past inputs in context window and retrieval-augmented
generation (RAG), frequently surface during human-LLM interactions, yet users are often …

Adanonymizer: Interactively Navigating and Balancing the Duality of Privacy and Output Performance in Human-LLM Interaction

S Zhang, X Yi, H **ng, L Ye, Y Hu, H Li - arxiv preprint arxiv:2410.15044, 2024 - arxiv.org
Current Large Language Models (LLMs) cannot support users to precisely balance privacy
protection and output performance during individual consultations. We introduce …

Personalized Reality: Challenges of Responsible Ubiquitous Personalization

J Strecker, S Mayer, K Bektas - Mensch und Computer 2024-Workshopband, 2024 - dl.gi.de
The expanding capabilities of Mixed Reality and Ubiquitous Computing technologies enable
personalization to be increasingly integrated with physical reality in all areas of people's …