基本信息
浏览量:358
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
个人简介
I led the work on benchmarking the data quality and deciding on key criteria such as data quantity, task distribution, length distribution, what values to align the models towards, whether we should use rating vs. ranking, etc. Apart from involving humans in the data collection processes for SFT and RLHF, we also experimented with AI distillation. Our Zephyr model is finetuned for alignment using only AI distilled data. My talk at NeurIPS '23 (slides available here) compared our work on using manual curation vs. AI distillation for alignment. The NYT covered my work on SFT and RLHF data collection and finetuning.
研究兴趣
论文共 64 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Weixin Liang,Nazneen Rajani, Xinyu Yang, Ezinwanne Ozoani,Eric Wu,Yiqun Chen,Daniel Scott Smith,James Zou
Nature Machine Intelligencepp.1-10, (2024)
Weixin Liang,Nazneen Rajani, Xinyu Yang, Ezinwanne Ozoani,Eric Wu,Yiqun Chen,Daniel Scott Smith,James Zou
CoRR (2024)
引用0浏览0EI引用
0
0
PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023pp.5805-5806, (2023)
Sarah Shoker,Andrew Reddie,Sarah Barrington,Miles Brundage, Husanjot Chahal, Michael Depp,Bill Drexel,Ritwik Gupta,Marina Favaro, Jake Hecla, Alan Hickey,Margarita Konaev,
CoRR (2023)
17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023pp.1019-1031, (2023)
引用0浏览0引用
0
0
arXiv (Cornell University) (2023)
arXiv (Cornell University)pp.359-370, (2022)
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn