Zhiyuan Zhang
Zhiyuan Zhang has 3 papers in our library, in 2021–2023, most of them on Language models & pretraining; often with Baobao Chang, Chuanqi Tan, Fei Huang.
OpenAlex · ORCID · h-index 18 · 149 works · 1,184 citations OpenAlex, 2026-10-14
📄 3 works in our library · 🔗 Cited 315 times in our library · ⭐ Paper Stars ranking: #3071
Affiliations
🎓Beijing Jiaotong UniversityBeijing ·
China2006–2025 · 39 papers🏛️Beijing Municipal Education CommissionBeijing ·
China2016–2025 · 15 papers🎓Civil Aviation University of ChinaTianjin ·
China2016–2025 · 5 papers🎓Dalian University of TechnologyDalian ·
China2023–2025 · 3 papers🎓Hubei University Of EconomicsWuhan ·
China2025 · 2 papers🎓Singapore Management UniversitySingapore ·
Singapore2023–2025 · 2 papers🎓Hong Kong Shue Yan UniversityHong Kong ·
China2025 · 1 paper🎓Liaoning Technical UniversityFuxin ·
China2025 · 1 paper🎓North University of ChinaTaiyuan ·
China2025 · 1 paper🎓Shandong Jiaotong UniversityJinan ·
China2025 · 1 paper
Concepts, shelves and topics
📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksArts and Humanities · 3 worksComputer Science · 3 worksLanguage and Linguistics · 3 works
🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 2 works
Works by year
2020s
Papers
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines (2023 · 261 citations)
Pipelines that chain language model calls usually depend on long prompt templates tuned by hand. These prompts are fragile and often fail to transfer across models, domains or inputs. The authors present DSPy, a Python programming model that borrows ideas from neural network frameworks such as PyTorch. Developers… - Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning (2021 · 200 citations)
When very large pretrained language models are fine-tuned on small labeled datasets, they tend to overfit and transfer poorly to new domains or related tasks. - Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models (2021 · 134 citations)
Backdoor attacks make an NLP classifier behave normally on ordinary inputs but output an attacker-chosen class whenever a rare trigger word appears.
Co-authors here
- Baobao Chang
- Chuanqi Tan
- Fei Huang
- Fuli Luo
- Keshav Santhanam
- Lei Li
- Matei Zaharia
- Omar Khattab
- Runxin Xu
- Songfang Huang
- Wenkai Yang
- Xu Sun
Venues
- Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2021
- Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2021
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhiyuan-zhang/