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

Yuhan Liu

2 indexed papers

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

Publications per year

2
26

Top categories

NLP×1AI×1ML×1Crypto×1Databases×1

Frequent co-authors

Ruoxi Su1×
Jingyu Hu1×
Abtin Mahyar1×
Masoumeh Shafieinejad1×
Xi He1×

Research Timeline

2026
FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models

The paper proposes FERMI, a method that significantly improves membership inference attacks against tabular diffusion models by leveraging auxiliary relational information available during training, even when only single-table features are visible at inference time.

Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision Alignment

The paper introduces an adaptive interview framework to gather rich persona context, demonstrating that LLMs improve decision alignment in moral dilemmas only when they selectively ground their decisions in follow-up-derived, user-specific evidence.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIRecentMay 28, 2026

Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision Alignment

Ruoxi Su, Yuhan Liu, Jingyu Hu

The paper introduces an adaptive interview framework to gather rich persona context, demonstrating that LLMs improve decision alignment in moral dilemmas only when they selectively ground their decisi…

View →
cs.LGcs.CRcs.DBRecentMay 12, 2026

FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models

Abtin Mahyar, Masoumeh Shafieinejad, Yuhan Liu, Xi He

The paper proposes FERMI, a method that significantly improves membership inference attacks against tabular diffusion models by leveraging auxiliary relational information available during training, e…

View →