Showing math.STShow all
2 papers · 1 filter
math.ST2025
Generalizing while preserving monotonicity in comparison-based preference learning models
Julien Fageot, Peva Blanchard, Gilles Bareilles +1
If you tell a learning model that you prefer an alternative over another alternative , then you probably expect the model to be monotone, that is, the valuation of incre…
math.ST2025
On Monotonicity in AI Alignment
Gilles Bareilles, Julien Fageot, Lê-Nguyên Hoang +4
Comparison-based preference learning has become central to the alignment of AI models with human preferences. However, these methods may behave counterintuitively. After empiricall…