1 code implementation • 22 May 2024 • Xiang Geng, Ming Zhu, Jiahuan Li, Zhejian Lai, Wei Zou, Shuaijie She, Jiaxin Guo, Xiaofeng Zhao, Yinglu Li, Yuang Li, Chang Su, Yanqing Zhao, Min Zhang, Hao Yang, Xinglin Lyu, Jiajun Chen, ShuJian Huang
For the second issue, we propose a method comprising two synergistic components: low-rank adaptation for training to maintain the original LLM parameters, and recovery KD, which utilizes data generated by the chat LLM itself to recover the original knowledge from the frozen parameters.
1 code implementation • 15 Jan 2024 • Wenhao Zhu, ShuJian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, Alexandra Birch
A typical solution is to translate instruction data into all languages of interest, and then train on the resulting multilingual data, which is called translate-training.
1 code implementation • 12 Jan 2024 • Shuaijie She, Wei Zou, ShuJian Huang, Wenhao Zhu, Xiang Liu, Xiang Geng, Jiajun Chen
To enhance reasoning abilities in non-dominant languages, we propose a Multilingual-Alignment-as-Preference Optimization framework (MAPO), aiming to align the reasoning processes in other languages with the dominant language.
no code implementations • 13 Nov 2023 • Shuaijie She, ShuJian Huang, Xingyun Wang, Yanke Zhou, Jiajun Chen
For answering the factual questions, which is more challenging, the average error rate of all evaluated LLMs is 36. 1%.
1 code implementation • 3 Dec 2022 • Shuaijie She, Xiang Geng, ShuJian Huang, Jiajun Chen
To separate the preference for factual consistency, we propose an unsupervised framework named CoP by controlling the preference of the generation model with the help of prompt.