Mitigating the Alignment Tax of RLHF
Authors:
- Hangyu LinHLHangyu Lin
- Shizhe DiaoSDShizhe Diao
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 580-606
Abstract
Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Evolutionary optimization of model merging recipesNature Machine Intelligence, 2025
- A Comprehensive Survey of Continual Learning: Theory, Method and ApplicationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Mathematical Analysis of Machine Learning Algorithms2023
- Finetune like you pretrain: Improved finetuning of zero-shot vision models2023
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2023
- ELLE: Efficient Lifelong Pre-training for Emerging Data2022
- Continual Sequence Generation with Adaptive Compositional Modules2022
- Continual Learning in Task-Oriented Dialogue Systems2021
- Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation2021
- Continual Learning for Text Classification with Information Disentanglement Based Regularization2021