Elamur Research⌕
☰
home / authors / Josef Dai

Josef Dai

Josef Dai has 2 papers in our library, in 2023–2025, most of them on Bias, fairness & safety, Language models & pretraining; often with Jiaming Ji, Borong Zhang, Mickel Liu.

2 papers in our library · 2023–2025

OpenAlex · h-index 2 · 5 works · 23 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 248 times in our library · ⭐ Paper Stars ranking: #4246

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 · China2024–2025 · 4 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 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 · 2 worksSocial Sciences · 2 works

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

 Works by year

2020s

20251 paperJosef Dai's papers of 202520231 paperJosef Dai's papers of 2023

 Papers

The most cited first (OpenAlex and our library).

  1. Safe RLHF: Safe Reinforcement Learning from Human Feedback (2023 · 207 citations)
    When large language models are tuned with RLHF, helpfulness and safety often pull against each other. A model that complies more readily may produce harmful content, while a model pushed hard toward safety may refuse too often. Annotators asked to give one combined preference also struggle to weigh these goals. The…
  2. PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025 · 81 citations)
    Safety alignment of large language models depends on preference data and fine-grained harm labels, which are expensive to collect at scale.

 Co-authors here

7 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 248 times (of the 141,840 papers whose bibliographies we read); 17 citing papers with a page here →.

Updated

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