← Search

Jeffrey George Wang

2 accepted papers

2026

Persona Features Control Emergent Misalignment

ICLR 2026poster

Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes "emergent misalignment," where models give stereotypically mali…

Cited by 0SourcecodeScholar
2023

MoPe: Model Perturbation based Privacy Attacks on Language Models

EMNLP 2023long main

Recent work has shown that Large Language Models (LLMs) can unintentionally leak sensitive information present in their training data. In this paper, we present Model Perturbations (MoPe), a new method to identify with high confidence if a given text is in the training data of a pre-trained languag…

Cited by 33SourceScholar