About

pfp.png

Hi, I'm Evan. I am an Electrical Engineering and Computer Science (EECS) master's student at UC Berkeley, advised by Professor Jiantao Jiao. I also completed my bachelor's degree in computer science at Berkeley.


My research focuses on Reinforcement Learning with Human Feedback (RLHF) for fine-tuning LLMs. Currently, much of my efforts revolve around reward model training and benchmarking.


I am also a Research Engineer at Nexusflow, where I work on training LLMs like Athene-70B. I also work with LMSYS, mainly on analyzing Chatbot Arena and building LLM benchmarks.

Select Publications

Starling-7B: Improving Helpfulness and Harmlessness with RLAIF. [COLM]

Banghua Zhu, Evan Frick, Tianhao Wu, Hanlin Zhu, Karthik Ganesan, Wei-Lin Chiang, Jian Zhang, and Jiantao Jiao. (2024).


From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline. [Neurips: In Review]

Tianle Li, Wei-Lin Chiang, Evan Frick, Lisa Dunlap, Tianhao Wu, Banghua Zhu, Joseph E. Gonzalez, and Ion Stoica. (2024).


Athene-70B: Redefining the Boundaries of Post-Training for Open Models.

Evan Frick, Peter Jin, Tianle Li, Karthik Ganesan, Jian Zhang, Jiantao Jiao, and Banghua Zhu. (2024).

Experience

Sky Lab | Researcher | May 24 - Present | Part-time

Working on Chatbot Arena and model evaluations.


Nexusflow | Machine Learning Engineer | Nov 23 - Present | Full-time

Improving chat models with RLHF. Training enterprise grade function calling LLMs.


Berkeley Artificial Intelligence Research | Researcher | Aug 23 - Present | Part-time

Making LLMs better with RLHF. Advised by Professor Jiantao Jiao.


Microsoft | Software Engineer Intern | May 23 - Aug 23 | Full-time

Worked on an all-encompassing environment-level change tracking and analytics system.


UC Berkeley CDSS | Undergraduate Researcher| Jan 23 - May 23 | Part-time

Researched Vision Transformer robustness in the dermatology domain.


Microsoft | Software Engineer Intern | May 22 - Aug 22 | Full-time

Worked on secure server allocation systems for a 10,000 server build environment.


Chess.com | Software Intern | Jun 21 - Aug 21 | Full-time

Made buttons button, clicks click, and moves move.

Education

UC Berkeley Electrical Engineering and Computer Science | 2024 - Present

M.S. in Electrical Engineering and Computer Science.


UC Berkeley Computing, Data Science, and Society | 2020 - 2024

B.A. in Computer Science, Minor in Data Science, Highest Distinction in General Scholarship.

Contact

Email: evanfrick[at]berkeley[dot]edu

Google Scholar: Evan Frick

LinkedIn: Evan Frick

Twitter: @evan_a_frick