Elamur Research⌕
☰
home / authors / Zeming Wei

Zeming Wei

Zeming Wei has 2 papers in our library, in 2023–2026, most of them on Bias, fairness & safety, Language models & pretraining, Interpretability; often with Ang Li, Cheng Wang, Muhao Chen.

2 papers in our library · 2023–2026

OpenAlex · ORCID · h-index 8 · 45 works · 228 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 135 times in our library · ⭐ Paper Stars ranking: #6380

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

🎓Peking UniversityBeijing · China2022–2026 · 31 paperscurrent🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2026 · 2 paperscurrent🎓Sun Yat-sen UniversityGuangzhou · China2026 · 1 papercurrent🎓South China Normal UniversityGuangzhou · China2021–2024 · 6 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 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 1 workArts and Humanities · 1 workComputer Science · 1 workLanguage and Linguistics · 1 work

🧭 Topics 3Research subjects and languages the work is about.Bias, fairness & safety · 2 worksLanguage models & pretraining · 1 workInterpretability · 1 work

 Works by year

2020s

20261 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations (2023 · 130 citations)
    Aligned LLMs can still be manipulated into producing harmful output. Existing jailbreaks are either expensive, relying on iterative optimization as in GCG or AutoDAN, or rigid hand-written templates. Wei et al. show that in-context learning alone can push a model's safety behaviour in either direction.
  2. False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize (2026 · 5 citations)
    The paper asks whether lightweight probes trained on LLM hidden states actually detect harmful intent, or only appear to.

 Co-authors here

6 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 135 times (of the 149,439 papers whose bibliographies we read); 33 citing papers with a page here →.

Updated

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