Xiang Lisa Li
Stanford NLP PhD; first author of Prefix-Tuning and the Contrastive Decoding / DExperts line of LM-steering papers.
- Role
- researcher
- Currently at
- Stanford University
- twitter.com/xiangli
- GitHub
- github.com/XiangLi1999
- Scholar
- scholar.google.com/citations
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9s1: Simple Test-Time Scaling
preprint
Auditing Prompt Caching in Language Model APIs
arXiv 2025
AutoBencher: Creating Salient, Novel, Difficult Datasets for Language Models
arXiv 2024
Learning to Compress Prompts with Gist Tokens
NeurIPS 2023 11
On the Learnability of Watermarks for Language Models
arXiv 2023
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
arXiv 2022
Diffusion-LM Improves Controllable Text Generation
arXiv 2022
Contrastive Decoding: Open-ended Text Generation as Optimization
arXiv 2022
Prefix-Tuning: Optimizing Continuous Prompts for Generation
ACL 2021 5
Affiliations
Frequent co-authors
10from 9 papers
Percy Liang
professor
Tatsunori Hashimoto
professor
Chenchen Gu
Luke Zettlemoyer
professor
Ari Holtzman
Christopher Potts
Daniel Fried
professor
David Hall
Emmanuel Candès
professor
Evan Zheran Liu