google scholar ▪ linkedin ▪ github

Some of my research:

• Towards Understanding Sycophancy in Language Models [2023, published at ICLR 2024]: LLMs trained with Reinforcement Learning from Human Feedback show sycophantic behavior which may be caused by human preferences

• The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" [2023, published at ICLR 2024]: LLMs fail to represent facts in an order-invariant way

• Constitutional classifiers: Defending against universal jailbreaks across thousands of hours of red teaming [2025]

• Many-shot Jailbreaking [published at NeurIPS 2024]

• • Taken out of context: On measuring situational awareness in LLMs [2023]: LLMs can successfully pass tests in-context having only seen descriptions of the tests in their training data

  • Forecasting Rare Language Model Behaviors [2025]: We introduce a method that forecasts risks in deployment across OOMs more queries than tested in evaluation 

• Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training [2024]: We find that deceptive behaviors in LLMs can resist standard safety training techniques

• Auditing Language Models for Hidden Objectives [2025]

• Evaluating feature steering: A case study in mitigating social biases [2024]

• Steering Llama 2 via Contrastive Activation Addition [2023, published at ACL 2024]: We develop a technique to control language model outputs by adding steering vectors to activations during inference

If you want to hear me talk: