Alexander Pan, Erik Jones, Meena Jagadeesan, Jacob Steinhardt. Feedback Loops With Language Models Drive In-Context Reward Hacking. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. pages 39154-39200, OpenReview.net, 2024. [doi]
@inproceedings{PanJJS24,
title = {Feedback Loops With Language Models Drive In-Context Reward Hacking},
author = {Alexander Pan and Erik Jones and Meena Jagadeesan and Jacob Steinhardt},
year = {2024},
url = {https://openreview.net/forum?id=EvHWlYTLWe},
researchr = {https://researchr.org/publication/PanJJS24},
cites = {0},
citedby = {0},
pages = {39154-39200},
booktitle = {Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024},
publisher = {OpenReview.net},
}