Research / Project detail

LLM safety & trustworthy generation

Research and engineering across dynamic attack–defense, closed-loop training, and detection–response separation; the related project received the Beijing Science and Technology Progress Award, Second Prize.

AlignmentSafetyTrustworthy AI
Problem

How can protection against evolving jailbreaks, harmful content, and hallucinations preserve useful task performance?

Method

Attack generation → evaluation → safety training → online protection → experience feedback. Related work includes TriPlay-RL and Magic-Token safety control.

Outcomes

The work includes TriPlay-RL, Magic Token, detection–response separation, and trustworthy generation. The related project received the Beijing Science and Technology Progress Award, Second Prize. “Key Technologies and Applications of Large-Model Safety” passed a CAAI technology achievement appraisal on June 19, 2025.

LLM safety and trustworthy generation framework
LLM safety and trustworthy generation framework
Online protection pipeline
Online protection pipeline
Related publications

Related papers

Related coverage

Related coverage