← Search

Zhiyi Tian

2 accepted papers

2026

Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation

ICML 2026poster

Jailbreak prompts can trigger harmful comple- tions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trig- ger refusal while preserving benign utility. How- ever, existing steering methods are fundamentally supe…

Cited by 0SourceScholar
2025

Introducing Graph Context into Language Models through Parameter-Efficient Fine-Tuning for Lexical Relation Mining

ACL 2025long

Lexical relation refers to the way words are related within a language. Prior work has demonstrated that pretrained language models (PLMs) can effectively mine lexical relations between word pairs. However, they overlook the potential of graph structures composed of lexical relations, which can be i…