Sijia Jing

Ph.D. Student @ Nanjing University · LLM & Agent Safety Alignment

I am a Ph.D. student at Nanjing University, advised by Prof. Yang Gao, and a member of the Reasoning and Learning Research Group. My research focuses on the safety alignment of large language models and agentic systems, with an emphasis on multi-turn jailbreak robustness and trajectory-level risk modeling.

Nanjing, China · Ph.D. @ Nanjing University (2025–present) · B.S. @ Henan University (2021–2025)

News 🔥

2026.05: Our paper PIARS on progressive induction-aware safety alignment is accepted to Machine Learning (Springer).
2026.01: Our paper SafeDialBench is accepted to ICLR 2026.
2025.06: Awarded Outstanding Undergraduate Thesis of Henan Province.
2023.10: Received the National Scholarship for Undergraduate Students (Top 1 in School).

Research Interests 🔬

LLM safety and multi-turn jailbreak robustness
Agentic reinforcement learning under safety constraints
Trajectory-level risk modeling and evaluation
Representation learning for alignment

Publications 📄

SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks

ICLR 2026

Paper Project Page GitHub

Hongye Cao*, Sijia Jing*, Yanming Wang*, Ziyue Peng*, Zhixin Bai, Zhe Cao, Meng Fang, Fan Feng, Jiaheng Liu, Boyan Wang, Tianpei Yang, Jing Huo, Yang Gao, Fanyu Meng, Xi Yang, Chao Deng, Junlan Feng

Progressive Induction-Aware Optimization for LLMs Safety Under Multi-turn Jailbreaks

Machine Learning (Springer), 2026

Paper GitHub

Sijia Jing*, Hongye Cao*, Boyan Wang, Jing Huo, Yang Gao

* Equal contribution.

Honors & Awards 🏆

2025: Outstanding Undergraduate Thesis, Henan Province
2025: Outstanding Graduate, Henan Province
2023: National Scholarship for Undergraduate Students
First Prize, China Robotics and AI Competition (National Final)

Education 🎓

2025–present: Ph.D., Nanjing University
2021–2025: B.S., Henan University