Jiancong Xiao
Scholar

Jiancong Xiao

Google Scholar ID: _vGY3joAAAAJ
University of Pennsylvania
Learning TheoryStatisticsOptimization
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
283
 
H-index
11
 
i10-index
12
 
Publications
18
 
Co-authors
11
list available
Contact
No contact links provided.
Publications
8 items
Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
2025
Cited
0
Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching
2025
Cited
0
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
2025
Cited
0
Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium
2025
Cited
0
Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Models Alignment
arXiv.org · 2024
Cited
3
Preserving Diversity in Supervised Fine-Tuning of Large Language Models
2024
Cited
4
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
2024
Cited
2
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
arXiv.org · 2024
Cited
26
Resume (English only)
Co-authors
11 total
Zhi-Quan Luo
Zhi-Quan Luo
Professor, The Chinese University of Hong Kong, Shenzhen, China
Weijie Su
Weijie Su
Associate Professor, University of Pennsylvania
Yanbo Fan
Yanbo Fan
Nanjing University
Qi Long
Qi Long
Professor, University of Pennsylvania
Ruoyu Sun
Ruoyu Sun
Chinese University of Hong Kong (Shenzhen), Shenzhen Institue of Big Data
Ziniu Li
Ziniu Li
The Chinese University of Hong Kong, Shenzhen
Zeyu Qin
Zeyu Qin
Hong Kong University of Science and Technology
Bojian Hou
Bojian Hou
Meta