Xuansheng Wu
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders
arXiv 2026
Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
arXiv 2024
InFoBench: Evaluating Instruction Following Ability in Large Language Models
arXiv 2024
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers