AI RESEARCH
MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment
arXiv CS.CL
•
ArXi:2603.18637v1 Announce Type: cross We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanced at once: multi-turn safety alignment, low over-refusal on benign boundary queries, and instruction following under verifiable constraints. We propose MOSAIC (Multi-Objective Slice-Aware Iterative Curation for Alignment), a multi-objective framework for closed-loop data mixture search built on a unified L1-L3 evaluation interface.