SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Yet safety alignment is still dominated by single-turn data and fixed-template dialogues, leaving a mismatch between training and deployment. To bridge this gap, we propose SaFeR-Steer, a progressive multi-turn alignment framework that combines staged synthetic bootstrapping with tutor-in-the-loop GRPO to train a single student under adaptive, on-policy attacks. We also introduce Trajectory-Consistent Summative Reward (TCSR), which aggregates the historical minimum and average of turn rewards so that any low-qual...
| Authors | Haolong Hu, Hanyu Li, Tiancheng He et al. |
|---|---|
| Primary category | cs.LG |
| Published | 18 March 2026 |
| Last updated at source | 11 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.