About Me

I am a Research Scientist at xAI. I obtained my Ph.D. in Computer Science from University of Illinois at Urbana-Champaign in 2024. I have also spent time at Google DeepMind, NVIDIA, Amazon, and an LLM startup.

I am enthusiastic about pushing the boundaries of foundation models through algorithms and (synthetic) data, with a recent interest in general knowledge and reasoning.

News

Follow @jefffhj
[08/2024] We release Grok-2 [blog]
[04/2024] Defend my Ph.D. dissertation: On the Capabilities and Risks of Large Language Models [pdf]
[12/2023] Serve as an Area Chair for ACL and NAACL 2024 (Action Editor for ARR).
[10/2023] New critique paper: Large Language Models Cannot Self-Correct Reasoning Yet [pdf]
[08/2023] We introduce RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models [pdf]
[07/2023] New position paper: Citation: A Key to Building Responsible and Accountable Large Language Models [pdf]
[05/2023] Two new preprints on the analysis of privacy leakage risks in LLMs and ChatGPT. [Quantifying Association] [Multi-step Jailbreaking Privacy Attacks]
[12/2022] New survey: Towards Reasoning in Large Language Models [pdf] [paperlist]
[05/2022] Are Large Pre-Trained Language Models Leaking Your Personal Information? [pdf] [media coverage]