Elamur Research⌕
☰
home / authors / Zhipeng Wang

Zhipeng Wang

Zhipeng Wang has 2 papers in our library, in 2026, most of them on Bias, fairness & safety; often with Jindong Gu, Qianzi Hou, Qizhuo Xie.

2 papers in our library · 2026

OpenAlex · ORCID · h-index 8 · 26 works · 285 citations OpenAlex, 2026-10-14

📄 2 works in our library · ⭐ Paper Stars ranking: #14131

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

🎓Nanjing Agricultural UniversityNanjing · China2024–2026 · 4 paperscurrent🎓Xidian UniversityXi'an · China2025–2026 · 4 paperscurrent🏥First Affiliated Hospital of Jiangxi Medical CollegeNanchang · China2024–2025 · 7 papers🎓Nanchang UniversityNanchang · China2024–2025 · 7 papers🏥First Affiliated Hospital of Nanchang UniversityNanchang · China2024–2025 · 6 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 workSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 1Research subjects and languages the work is about.Bias, fairness & safety · 1 work

 Works by year

2020s

20262 papers

 Papers

The most cited first (OpenAlex and our library).

  1. CoDA: Restoring Contextual Dominance via Copy-Encouraged Attention Intervention for Mitigating RAG Hallucinations (2026)
    The paper examines a specific RAG failure: the retrieved passage contains correct and sufficient evidence, yet the model still answers from its parametric memory. The authors treat this as a routing problem in the residual stream. Building on the ReDeEP decomposition, they measure two quantities per layer:
  2. You Only Need One Single Token to Refine Safety Alignment (2026)
    Safety-aligned LLMs often over-refuse: they reject prompts that look dangerous but are actually benign. Existing training-free fixes include prompting, contrastive decoding and activation steering. These add inference cost or depend on the specific architecture, and they correct outputs after the fact without…

 Co-authors here

5 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.

Updated

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