Elamur Research⌕
☰
home / authors / Daojing He

Daojing He

Daojing He has 3 papers in our library, in 2025, most of them on Bias, fairness & safety, Language models & pretraining; often with Jing Li, Jun Yu, Min Zhang.

3 papers in our library · 2025

OpenAlex · ORCID · h-index 47 · 250 works · 6,341 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 29 times in our library · ⭐ Paper Stars ranking: #8160

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

🎓Harbin Institute of TechnologyHarbin · China2008–2026 · 117 paperscurrent🎓East China Normal UniversityShanghai · China2013–2026 · 85 paperscurrent🎓Nanchang UniversityNanchang · China2020–2026 · 12 paperscurrent🎓Zhejiang UniversityHangzhou · China2010–2014 · 28 papers🎓South China University of TechnologyGuangzhou · China2013–2017 · 12 papers🎓Jiangxi University of Science and TechnologyGanzhou · China2018–2025 · 8 papers🔬Shanghai Key Laboratory of Trustworthy ComputingShanghai · China2015–2017 · 4 papers🎓Hainan Normal UniversityHaikou · China2020 · 2 papers🎓Suzhou Vocational UniversitySuzhou · China2019–2020 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksComputer Vision and Pattern Recognition · 1 work

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

 Works by year

2020s

20253 papers

 Papers

The most cited first (OpenAlex and our library).

  1. MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming (2025 · 14 citations)
    Jailbreak research and safety training have mostly targeted single-turn prompts. In multi-turn chats, an attacker can spread harmful intent across several innocent-looking turns, and LLMs are more likely to give in. MTSA is a two-stage framework for multi-turn safety.
  2. Safety Alignment via Constrained Knowledge Unlearning (2025 · 13 citations)
    Aligned large language models still produce harmful content under jailbreak attacks. The authors argue this happens because standard defenses, such as continued safety training, teach models to refuse without removing the dangerous knowledge itself, and they can also erode general skills. They propose Constrained…
  3. Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer (2025 · 11 citations)
    Fine-tuned checkpoints of foundation models often generalize poorly beyond their target domain and contain many redundant weight changes.

 Co-authors here

9 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 29 times (of the 149,439 papers whose bibliographies we read); 11 citing papers with a page here →.

Updated

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