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

Haifeng Xu

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

NLP×1AI×1Stats ML×1

Frequent co-authors

Yuwei Cheng1×
Weiyi Tian1×

Research Timeline

2026
Fine-Tuning Improves Information Conveyance in Language Models

The paper introduces Canopy Entropy ($ ext{CE}^ ext{*}$), a novel metric that quantifies generation uncertainty across the entire output space, demonstrating that fine-tuning improves information conveyance by efficiently converting token uncertainty into semantic diversity.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIstat.MLRecentMay 29, 2026

Fine-Tuning Improves Information Conveyance in Language Models

Yuwei Cheng, Weiyi Tian, Haifeng Xu

The paper introduces Canopy Entropy ($ ext{CE}^ ext{*}$), a novel metric that quantifies generation uncertainty across the entire output space, demonstrating that fine-tuning improves information conv…

View →