Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment
Tony Tu, Sayan Chakraborty, Ruomeng Xu +2
Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization collapses o…
cs.AI2026
Improving the Safety and Trustworthiness of Medical AI via Multi-Agent Evaluation Loops
Zainab Ghafoor, Md Shafiqul Islam, Koushik Howlader +6
Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This…