Jujie He

Jujie He has 2 papers in our library, in 2024, most of them on Language models & pretraining, Reasoning; often with Liang Zeng, Shuicheng Yan, Yahui Zhou.

2 papers in our library · 2024

The profile is the library's match of the name; two people with one name are not always told apart.

Topics

The most cited first (OpenAlex and our library).

Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs (2024 · 104 citations)
Reward models turn human preferences into a training signal for LLM alignment. Their quality depends heavily on the preference data, and open-source preference datasets tend to be noisy or inconsistently labelled. The authors take a data-first approach. Using only public sources (HelpSteer2, OffsetBias, WildGuardMix…
Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models — The Story Goes On (2024 · 14 citations)
The paper asks whether strong mathematical reasoning really requires very large models, and whether supervised fine-tuning (SFT) only changes output style.

2 more works of theirs are in our library without a page here yet; they will appear as we publish them.

11 co-authors with a page, the most papers together first.

Papers of our library cite their works 163 times (of the 140,884 papers whose bibliographies we read); 3 citing papers with a page here →.