SOURCE-LINKED INTELLIGENCE

Suan: Rectifying Direct Preference Safety Alignment in Large Language Models

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Integrating robust safety guardrails into Large Language Models (LLMs) is essential for delivering helpful yet harmless responses. While proprietary systems exhibit reliable safety controls, their underlying methodologies and trade-offs remain largely undisclosed. Achieving comparable security in open-weight models remains a persistent challenge, as post-trained variants frequently suffer from over-refusal and degraded general quality. To overcome these drawbacks, we introduce Suan, a novel preference optimization algorithm. Unlike existing methods, we formulate the optimization objective dire

Read original source ↗ Open in workspace

recordType

paper

region

Global