(* indicates equal contribution)
ALaRM: Align Language Models via Hierarchical Rewards Modeling
ACL 2024 Findings
Yuhang Lai, Siyuan Wang, Shujun Liu, Xuanjing Huang, Zhongyu Wei
[paper] [code] [page]
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
ICML 2023
Yuhang Lai*, Chengxi Li*, Yiming Wang*, Tianyi Zhang*, Ruiqi Zhong*, Luke Zettlemoyer, Scott Wen-tau Yih, Daniel Fried, Sida Wang, Tao Yu
[paper] [code] [page] [data]
ARKS: Active Retrieval in Knowledge Soup for Code Generation
EMNLP 2024 Findings
Hongjin Su, Shuyang Jiang, Yuhang Lai, Haoyuan Wu, Boao Shi, Che Liu, Qian Liu, Tao Yu
[paper] [code] [page] [data]
HAF-RM: A Hybrid Alignment Framework for Reward Model Training
arXiv 2024
Shujun Liu, Xiaoyu Shen, Yuhang Lai, Siyuan Wang, Shengbin Yue, Zengfeng Huang, Xuanjing Huang, Zhongyu Wei
[paper] [code] [page]
Mar 31, 2023
ChatGPT和GPT-4的出现给NLP从业者带来的影响是巨大的，我在知乎上看到了一个有趣的观点。
Nov 28, 2022
现在是北京时间凌晨3:30，我和舍友正在通宵收拾行李，准备在凌晨5:00的时候坐班车离开学校。