Jinghui Chen
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
arXiv 2026
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time
arXiv 2025
Backdoor Contrastive Learning via Bi-level Trigger Optimization
arXiv 2024
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers