Shiyue Zhang
@byryuer.bsky.social
Research Engineer at Bloomberg | ex PhD student at UNC-Chapel Hill | ex Bloomberg PhD Fellow | ex Intern at MetaAI, MSFTResearch | #NLProc
https://zhangshiyue.github.io/#/
https://zhangshiyue.github.io/#/
🚨 First ever post here~ New paper out! Instruct models are not always the best. Scaling down 📉 instruction tuning strength via partial adaptation leads to material gains 🚀 on few-shot in-context learning NLP tasks across model families and sizes.
arxiv.org/abs/2504.11626
arxiv.org/abs/2504.11626
April 17, 2025 at 8:55 PM
🚨 First ever post here~ New paper out! Instruct models are not always the best. Scaling down 📉 instruction tuning strength via partial adaptation leads to material gains 🚀 on few-shot in-context learning NLP tasks across model families and sizes.
arxiv.org/abs/2504.11626
arxiv.org/abs/2504.11626