Showing cs.LGShow all
3 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…
cs.LG2025
Size-adaptive Hypothesis Testing for Fairness
Antonio Ferrara, Francesco Cozzi, Alan Perotti +2
Determining whether an algorithmic decision-making system discriminates against a specific demographic typically involves comparing a single point estimate of a fairness metric aga…
cs.LG2025
Bounded-Abstention Pairwise Learning to Rank
Antonio Ferrara, Andrea Pugnana, Francesco Bonchi +1
Ranking systems influence decision-making in high-stakes domains like health, education, and employment, where they can have substantial economic and social impacts. This makes the…