Ethically Aligned Reward Models: A Language Model Post-Training Framework
 dati |
 bibtex |
@courseproject{cridligsangiorgifossa2425-ethicsofai20242025,
abstract = {Aligning Language Models (LMs) with human moral values is a critical challenge in the development of responsible AI systems. Reward Models play a central role in this process by enabling post-training alignment through Reinforcement Learning from Human Feedback (RLHF) [2]. In this project, we leverage the ETHICS dataset [1] to investigate the extent to which modern Reward Models can represent and generalize ethical concepts. Using open-source tools, we plan to create morally congruent Reward Models aligned with shared human values, intended for integration into RLHF pipelines. Our goal is to develop a prototype framework capable of evaluating and guiding LMs toward ethically preferable outputs.},
apice = {CridligSangiorgiFossa2425},
author = {Nicolas Cridlig and Marco Sangiorgi and Andrea Fossa},
howpublished = {Ethics of AI, A.Y. 2024/2025},
sort = {classic},
supervisor = {Calegari, Roberta},
title = {Ethically Aligned Reward Models: A Language Model Post-Training Framework},
type = {Standard Project},
url = {https://dvcs.apice.unibo.it/pika-lab/courses/ai-ethics/projects/cridligsangiorgifossa2425}
}
abstract = {Aligning Language Models (LMs) with human moral values is a critical challenge in the development of responsible AI systems. Reward Models play a central role in this process by enabling post-training alignment through Reinforcement Learning from Human Feedback (RLHF) [2]. In this project, we leverage the ETHICS dataset [1] to investigate the extent to which modern Reward Models can represent and generalize ethical concepts. Using open-source tools, we plan to create morally congruent Reward Models aligned with shared human values, intended for integration into RLHF pipelines. Our goal is to develop a prototype framework capable of evaluating and guiding LMs toward ethically preferable outputs.},
apice = {CridligSangiorgiFossa2425},
author = {Nicolas Cridlig and Marco Sangiorgi and Andrea Fossa},
howpublished = {Ethics of AI, A.Y. 2024/2025},
sort = {classic},
supervisor = {Calegari, Roberta},
title = {Ethically Aligned Reward Models: A Language Model Post-Training Framework},
type = {Standard Project},
url = {https://dvcs.apice.unibo.it/pika-lab/courses/ai-ethics/projects/cridligsangiorgifossa2425}
}