MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment

Computer Science > Cryptography and Security [Submitted on 19 Mar 2026] MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment Yipu Dou, Wang Yang 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. MOSAIC turns slice-level failure profiles into executable data actions, including dataset-level mixture ratios, bucket-level weights, and focus criteria. Under a fixed 1M-token budget and five rounds of independent fine-tuning from the same base model, MOSAIC improves internal XGuard from 2.76 to 4.67 while keeping OrBench at 4.41 and IFEval at 3.65. The final Pareto solution also generalizes better than a random static LoRA baseline on independent attack, over-refusal, and capability tests, suggesting that structured failure diagnosis can serve as a practical control signal for budgeted data construction. Code is available at this https URL. Comments: 9 pages, 5 figures. Code available at this https URL Subjects: Cryptography and Security (cs.CR); Computation and Language (cs.CL) Cite as: arXiv:2603.18637 [cs.CR]   (or arXiv:2603.18637v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.18637 Focus to learn more Submission history From: Yipu Dou [view email] [v1] Thu, 19 Mar 2026 09:00:47 UTC (123 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)