Manacá-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge

Bruno Leonardo Santos Menezes, Carlos Leonardo Souza Cardoso, Fabio André Machado Porto|October 14, 2026arXiv

Key Takeaway

When aligning models for underserved languages, document what doesn't work (like DPO failures), use statistical rigor in comparisons, and watch for silent failures in LLM-based evaluation—judges may refuse to score items without warning, invalidating results.

Summary

This paper presents Manacá-1B-Instruct-2, a safety-aligned Brazilian Portuguese language model, documenting failed DPO experiments and successful safety alignment through iterative SFT.

safety training evaluation

Key Terms

dpo sft safety-tuning llm-judge