Jiaxiang Li

works on

convex optimization 1 dynamic batch size 1 large language models 1 learning rate schedule 1 scaling laws 1

From the 1 of 10 linked papers with an AI index.

activity

20242026

collaborators

Showing cs.AIShow all

1 paper · 1 filter

cs.AI2024

Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment

Jiaxiang Li, Siliang Zeng, Hoi-To Wai +3

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (…