Showing 2026Show all
2 papers · 1 filter
cs.LG2026
BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment
Antonio Ferrara, Alberto Rumi, Francesco Bonchi
Preference-based alignment methods such as Direct Preference Optimization (DPO) use pairwise preferences labeled by human annotators to fine-tune language models. However, annotato…
math.NT2026
Surviving Eratosthenes sieve I: quadratic density and Legendre's conjecture
Fred B. Holt
We have been studying Eratosthenes sieve as a discrete dynamic system, obtaining exact models for the relative populations for small gaps (currently gaps ) in the cycle o…