Alex Beutel

Alex Beutel

OpenAI

About Me

I am currently the tech lead for our Safety Research teams at OpenAI.

I was previously a senior staff research scientist, tech lead, and manager at Google Research, co-leading a Responsible ML team and driving research spanning recommender systems, fairness, robustness, reinforcement learning, and machine learning for databases. I led work from basic research to product impact, with >50 launches across multiple products.

I got my Ph.D. in computer science at Carnegie Mellon University, advised by Christos Faloutsos and Alex Smola. My thesis research focused on large-scale user behavior modeling, covering fraud detection, recommender systems, and scalable machine learning. Over the course of graduate school, I interned with Facebook's Site Integrity team and News Feed Ranking teams, Microsoft's Cloud and Information Service Lab, and Google Research.

Before graduate school, I majored in computer science and physics at Duke University. While there, I worked with Pankaj Agarwal and Thomas Mølhave on computational geometry for terrain modeling.

Email me at or contact me on Twitter or LinkedIn.

Select Publications (Complete List, DBLP, Google Scholar)

AI Safety

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
...Eric Wallace*, Kai Xiao*, Reimar Leike*, Lilian Weng, Johannes Heidecke, Alex Beutel
Preprint, 2024
Practices for Governing Agentic AI Systems
...Yonadav Shavit, Sandhini Agarwal, Miles Brundage, Steven Adler, Cullen O’Keefe, Rosie Campbell, Teddy Lee, Pamela Mishkin, Tyna Eloundou, Alan Hickey, Katarina Slama, Lama Ahmad, Paul McMillan, Alex Beutel, Alexandre Passos, David G. Robinson
White paper, 2023
PDF
Controlled Decoding from Language Models
...Sidharth Mudgal, Jong Lee, Harish Ganapathy, YaGuang Li, Tao Wang, Yanping Huang, Zhifeng Chen, Heng-Tze Cheng, Michael Collins, Jilin Chen, Alex Beutel, Ahmad Beirami
ICML, 2024
PDF

Recommendation Systems

Building Healthy Recommendation Sequences for Everyone: A Safe Reinforcement Learning Approach
...Ashudeep Singh, Yoni Halpern, Nithum Thain, Konstantina Christakopoulou, Ed H. Chi, Jilin Chen, Alex Beutel
FAccTRec, 2020
PDF
Top-K Off-Policy Correction for a REINFORCE Recommender System
...Minmin Chen*, Alex Beutel*, Paul Covington*, Sagar Jain, Francois Belletti, Ed H. Chi
WSDM, 2019
PDF
Latent Cross: Making Use of Context in Recurrent Recommender Systems
...Alex Beutel, Paul Covington, Sagar Jain, Can Xu, Jia Li, Vince Gatto, Ed H. Chi
WSDM, 2018
PDF
Recurrent Recommender Networks
...Chao-Yuan Wu, Amr Ahmed, Alex Beutel, Alex Smola, How Jing
WSDM, 2017
PDF

Fairness

First-Person Fairness in Chatbots
...Tyna Eloundou, Alex Beutel, David G. Robinson, Keren Gu-Lemberg, Anna-Luisa Brakman, Pamela Mishkin, Meghan Shah, Johannes Heidecke, Lilian Weng, Adam Tauman Kalai
Preprint, 2024
PDF
Measuring and Reducing Gendered Correlations in Pre-trained Models
...Kellie Webster, Xuezhi Wang, Ian Tenney, Alex Beutel, Emily Pitler, Ellie Pavlick, Jilin Chen, Ed H. Chi, Slav Petrov
Preprint, 2020
PDF
- Blog post
Fairness without Demographics through Adversarially Reweighted Learning
...Preethi Lahoti, Alex Beutel, Jilin Chen, Kang Lee, Flavien Prost, Nithum Thain, Xuezhi Wang, Ed H. Chi
NeurIPS, 2020
PDF Appendix Code
Fairness in Recommendation Ranking through Pairwise Comparisons
...Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Li Wei, Yi Wu, Lukasz Heldt, Zhe Zhao, Lichan Hong, Ed H. Chi, Cristos Goodrow
KDD (Applied Data Science Track), 2019
PDF Video
- Incorporated in a large-scale production recommender (Google Research's 2019 Year in Review).
Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements
...Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Allison Woodruff, Christine Luu, Pierre Kreitmann, Jonathan Bischof, Ed H. Chi
AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2019
PDF

Robustness

Striving for data-model efficiency: Identifying data externalities on group performance
...Esther Rolf, Ben Packer, Alex Beutel, Fernando Diaz
Trustworthy and Socially Responsible Machine Learning (TSRML) workshop at NeurIPS, 2022
PDF
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
...Yao Qin, Chiyuan Zhang, Ting Chen, Balaji Lakshminarayanan, Alex Beutel, Xuezhi Wang
NeurIPS, 2022
PDF
Improving Calibration through the Relationship with Adversarial Robustness
...Yao Qin, Xuezhi Wang, Alex Beutel, Ed H. Chi
NeurIPS, 2021
PDF
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation
...Tianlu Wang, Xuezhi Wang, Yao Qin, Ben Packer, Kang Li, Jilin Chen, Alex Beutel, Ed H. Chi
EMNLP, 2020
PDF

Machine Learning Systems

The Case for Learned Index Structures
...Tim Kraska, Alex Beutel, Ed H. Chi, Jeffrey Dean, Neoklis Polyzotis
SIGMOD, 2018
PDF ML Systems at NeurIPS 2017 North East Database Day 2018 SysML 2018
Learned Indexes for a Google-scale Disk-based Database
...Hussam Abu-Libdeh, Deniz Altinbuken, Alex Beutel, Ed H. Chi, Lyric Doshi, Tim Kraska, Xiaozhou, Li, Andy Ly, Christopher Olston
ML for Systems workshop at NeurIPS, 2020
PDF

Fraud Detection

CopyCatch: Stopping Group Attacks by Spotting Lockstep Behavior in Social Networks
...Alex Beutel, Wanhong Xu, Venkatesan Guruswami, Christopher Palow, Christos Faloutsos
WWW, 2013
PDF
- ACM Computing Review Editor's Highlight on CopyCatch
- Patent by Facebook (Patent Number 9077744)
- Discussion by Facebook
- Included in courses at Carnegie Mellon and University of Florida
(Best Paper Award) FRAUDAR: Bounding Graph Fraud in the Face of Camouflage
...Bryan Hooi, Hyun Ah Song, Alex Beutel, Neil Shah, Kijung Shin, Christos Faloutsos
KDD, 2016
PDF
- Winner of KDD 2016 Best Paper Award and CogX 2017 Award for Best Student Paper in AI
- Media: NSF, WESA - Pittsburgh NPR, TechXplore, Stanford Scholar, Crain's