Shujian Zhang
@zhang_shujian
Research Scientist @GoogleDeepmind | Ph.D. @UTAustin
ID: 1282129122333007872
https://szhang42.github.io/ 12-07-2020 01:46:24
20 Tweet
39 Takipçi
49 Takip Edilen
🚨 Excited to share our new preprint with Shujian Zhang, Wenxuan Zhou, Marzyeh, and Sanqiang Zhao. 🚀 TLDR: We propose SFTMix, a novel recipe that elevates language model instruction tuning without relying on expensive, well-curated datasets. arxiv.org/abs/2410.05248
![How can LLM architecture recognize Instruction Hierarchy?
🚀 Excited to share our latest work on Instructional Segment Embedding (ISE)! A technique embeds Instruction Hierarchy directly into LLM architecture, significantly boosting LLM safety. 🧵[1/n]](https://pbs.twimg.com/media/GaB-XkuXsAAcxbU.png "Tong Wu (@tongwu_pton) on Twitter photo How can LLM architecture recognize Instruction Hierarchy?
🚀 Excited to share our latest work on Instructional Segment Embedding (ISE)! A technique embeds Instruction Hierarchy directly into LLM architecture, significantly boosting LLM safety. 🧵[1/n]")
📝 For more details and experiments, please check our arxiv: arxiv.org/abs/2410.09102 Thanks to all of my amazing collaborators 🙌 Wenxuan Zhou Shujian Zhang KaiqiangSong Silei Xu xcc Prof. Prateek Mittal and more colleagues from @zoom. 🧵[7/n]
