Author

Jiancong Xiao

h-index 6 View on Semantic Scholar

We have 2 of 10 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Aug 2026

Statistical impossibility and possibility of aligning LLMs with human preferences: From Condorcet paradox to Nash equilibrium

It is proved that Condorcet cycles exist with probability converging to one exponentially fast under a general probabilistic preference model called the Luce model, thereby demonstrating the impossibility of fully aligning human preferences using reward-based approaches such as reinforcement learning from human feedbac...

Kaizhao Liu, Qi Long, Zhekun Shi et al. · Annals of Statistics · 0 citations

Preprint Aug 2026

Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration

This work proposes maximizing the entropy of predictive distributions as the calibration objective, which directly targets overconfidence by discouraging overly concentrated predictions, and adopts an efficient first-order approximation that avoids explicit second-order computation.

Ruochen Jin, Zhanliang Wang, Zong-Yu Dai et al. · 0 citations