← Search

Shahrad Mohammadzadeh

2 accepted papers

2025

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

ACL 2025long

As large language models (LLMs) become increasingly prevalent, concerns about their reliability, particularly due to hallucinations - factually inaccurate or irrelevant outputs - have grown. Our research investigates the relationship between the uncertainty in training dynamics and the emergence of…

2025

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility

EMNLP 2025

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed fine-tuning APIs, can produce helpful-only models with safeguards de