Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xilai Fan

Xilai Fan

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×2

Frequent co-authors

Yikai Guo2×
Bin Wang2×
Wenjun Ke2×
Haoran Luo2×

Research Timeline

2026
On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective

The paper proposes 'Uncertainty,' a multiscale uncertainty estimator that focuses on low-probability tokens to improve the detection of AI-generated text by addressing boilerplate dominance and score brittleness.

On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective

The paper proposes 'Uncertainty,' a multiscale uncertainty estimator that focuses on low-probability tokens to improve the detection of AI-generated text by addressing boilerplate dominance and score brittleness.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentJun 1, 2026

On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective

Yikai Guo, Bin Wang, Xilai Fan, Wenjun Ke +1 more

The paper proposes 'Uncertainty,' a multiscale uncertainty estimator that focuses on low-probability tokens to improve the detection of AI-generated text by addressing boilerplate dominance and score…

View →
cs.CLRecentJun 1, 2026

On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective

Yikai Guo, Bin Wang, Xilai Fan, Wenjun Ke +1 more

The paper proposes 'Uncertainty,' a multiscale uncertainty estimator that focuses on low-probability tokens to improve the detection of AI-generated text by addressing boilerplate dominance and score…

View →