Zi Lin
current affiliationUniversity of California San Diego, San Diego, United States; Chengdu University, Chengdu, China; Fuzhou University, Fuzhou, China; University of South China, Hengyang, China
Zi Lin has 2 papers on this site, in 2023, most of them on Language models & pretraining, Bias, fairness & safety; often with Eric Xing, Ion Stoica, Jingbo Shang.
OpenAlex · ORCID · h-index 9 · 54 works · 355 citations OpenAlex, 2026-10-14
2 works on this site · 303 citations in our library · 1 more work in our library
Affiliations
- University of California San Diego · San Diego, United States — current · 2022–2024 on 7 papers
- Chengdu University · Chengdu, China — current · 2024 on 1 paper
- Fuzhou University · Fuzhou, China — current · 2024 on 1 paper
- University of South China · Hengyang, China — current · 2024 on 1 paper
- Google (United States) · Mountain View, United States — 2022–2023 on 5 papers
- Harvard University · Cambridge, United States — 2022–2023 on 3 papers
- Tai’an Maternity and Child Care Hospital · Tai’an, China — 2023 on 2 papers
- Chinese Academy of Sciences · Beijing, China — 2010 on 2 papers
- Jiaxing University · Jiaxing, China — 2005–2009 on 2 papers
Topics
Papers
- LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset (2023 · 235 citations)
Research into how people use large language models has been held back by the lack of public logs of genuine user interactions. - ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation (2023 · 127 citations)
Most toxicity detectors are trained on social media text. Users of LLM chatbots behave differently: they phrase harmful intent as questions or instructions, and they sometimes use "jailbreaking" prompts that look benign but aim to make the model bypass its policies. To study this gap, the authors built ToxicChat, the…
Also in our library
Co-authors here
- Eric Xing
- Ion Stoica
- Jingbo Shang
- Joseph E. Gonzalez
- Lianmin Zheng
- Tianle Li
- Wei-Lin Chiang
- Ying Sheng
- Zhuohan Li
- Zihan Wang
Cited by
This page in Markdown → https://md.research.elamur.ai/free/en/authors/zi-lin/