3 papers
cs.LG2026
How Many Different Outputs Can a Transformer Generate?
Maxime Meyer, Mario Michelessa, Caroline Chaux +1
We study how we can leverage only a handful of characteristics of a transformer's architecture to closely predict the number of different sequences it can output, both qualitativel…
cs.CL2026
Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization
Gabriel Loiseau, Damien Sileo, Damien Riquet +2
Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation varies with the data domain, privac…
cs.CL2026
Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models
Gabriel Loiseau, Damien Sileo, Damien Riquet +2
Accurate privacy evaluation of textual data remains a critical challenge in privacy-preserving natural language processing. Recent work has shown that large language models (LLMs)…