Xiting Wang
- Papers
- 6
Cite
Notes
Only stored in your browser.
6papers
Authored papers
6Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator
arXiv 2025
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
arXiv 2025
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
arXiv 2024
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
arXiv 2024
See or Guess: Counterfactually Regularized Image Captioning
arXiv 2024
Semi-Offline Reinforcement Learning for Optimized Text Generation
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 6 papers