Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models

Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models Somanshu Singla author Zhen Wang author Tianyang Liu author Abdullah Ashfaq author Zhiting Hu author Eric P Xing author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication singla-etal-2024-dynamic 10.18653/v1/2024.emnlp-main.1220 https://aclanthology.org/2024.emnlp-main.1220/ 2024-11 21889 21909