
Human Feedback in Reinforcement Learning Improves Chatbot Fairness
Adam Kalai
Research Scientist, AI Safety and Ethics, OpenAI
Research Scientist, AI Safety and Ethics, OpenAI
Adam Tauman Kalai is a Research Scientist at OpenAI, specializing in AI Safety and Ethics. His research spans algorithms, fairness, machine learning theory, game theory, and crowdsourcing. Adam earned his BA from Harvard University and his PhD from Carnegie Mellon University, after which he served as an Assistant Professor at both Georgia Tech and the Toyota Technological Institute at Chicago. He also contributes to Project CETI’s science team, an interdisciplinary initiative dedicated to decoding sperm whale communication. In addition, Adam has co-chaired leading conferences such as COLT (Conference on Learning Theory), HCOMP (Conference on Human Computation), and NEML. His work has been recognized with numerous honors, including several best paper awards, an NSF CAREER Award, an Alfred P. Sloan Fellowship, and most notably the Majulook Prize.
Learn more
Website: https://kal.ai/
Read these
First-Person Fairness in Chatbots by Tyna Eloundou, et al., 2024.
Calibrated language models must hallucinate by Adam Tauman Kalai and Santosh Vempala, 2024.
Using large language models to simulate multiple humans and replicate human subject studies by Gati Aher, Rosa Arriaga, and Adam Tauman Kalai, 2023.
Website: https://kal.ai/
Read these
First-Person Fairness in Chatbots by Tyna Eloundou, et al., 2024.
Calibrated language models must hallucinate by Adam Tauman Kalai and Santosh Vempala, 2024.
Using large language models to simulate multiple humans and replicate human subject studies by Gati Aher, Rosa Arriaga, and Adam Tauman Kalai, 2023.