Elamur Research⌕
☰
home / authors / Xinyang Han

Xinyang Han

Xinyang Han has 2 papers in our library, in 2025, most of them on Language models & pretraining, Bias, fairness & safety; often with An Zhang, Bing Qin, Jiahe Guo.

2 papers in our library · 2025

OpenAlex · h-index 4 · 21 works · 31 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 20 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #9104

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Jiangsu UniversityZhenjiang · China2025–2026 · 4 paperscurrent🎓University of California, BerkeleyBerkeley · United States2026 · 3 paperscurrent🏢State Grid Corporation of ChinaBeijing · China2017–2023 · 6 papers🎓Harbin Institute of TechnologyHarbin · China2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 worksSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 2Research subjects and languages the work is about.Bias, fairness & safety · 2 worksLanguage models & pretraining · 2 works

 Works by year

2020s

20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025 · 11 citations)
    Safety-aligned LLMs can still be jailbroken. Activation steering is a training-free defense that pushes hidden states toward refusal, but it applies one fixed strength to every input. That fixed setting under-protects against some attacks and causes more false refusals of harmless requests. AdaSteer makes the…
  2. Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025 · 9 citations)
    The paper examines how fine-tuning LLMs for character role-play affects their safety. The authors fine-tuned LLaMA-3-8B-Instruct separately for each of 95 characters from RoleBench. Role-play quality improved, but the models refused harmful AdvBench requests much less often, and villainous characters lost the most…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak DefenderConference on Empirical Methods in Natural Language Processing (EMNLP)Weixiang Zhao, Jiahe Guo, Yulin Hu, et al.2025 · 11 citations
  2. Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Weixiang Zhao, Yulin Hu, Yang Deng, et al.2025 · 9 citations
  3. JobBench: Aligning Agent Work With Human Will ↗arXiv (Cornell University) · no summary yetYuetai Li et al.2026 · 1 citation

 Co-authors here

10 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 20 times (of the 149,439 papers whose bibliographies we read); 6 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xinyang-han/