--- title: "Josef Dai · Peking University — author profile and papers" description: "Josef Dai, Peking University: 2 papers on Elamur Research (2023–2025), h-index 2 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/josef-dai/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/josef-dai/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Josef Dai # Josef Dai Josef Dai has 2 papers in our library, in 2023–2025, most of them on [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Jiaming Ji](https://md.research.elamur.ai/free/en/authors/jiaming-ji/), [Borong Zhang](https://md.research.elamur.ai/free/en/authors/borong-zhang/), [Mickel Liu](https://md.research.elamur.ai/free/en/authors/mickel-liu/). 2 papers in our library · 2023–2025 [OpenAlex](https://openalex.org/A5099380859) · [**h-index 2**](https://openalex.org/authors/A5099380859) · [5 works](https://openalex.org/works?filter=author.id:A5099380859) · [23 citations](https://openalex.org/works?filter=author.id:A5099380859&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/josef-dai/#papers) · [🔗 Cited 248 times in our library](https://md.research.elamur.ai/free/en/authors/josef-dai/cited-by/) · [⭐ Paper Stars ranking: #4246](https://md.research.elamur.ai/free/en/paper-stars/page/43/#star-4246) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Josef+Dai) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Josef+Dai) · [dblp](https://dblp.org/search?q=Josef+Dai) · [ACL Anthology](https://aclanthology.org/search/?q=Josef+Dai) ## Affiliations [🎓**Peking University** Beijing · China 2024–2025 · 4 papers*current*](https://md.research.elamur.ai/free/en/universities/peking-university/) 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. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Safety Research · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/) 🧭 Topics 2 Research subjects and languages the work is about.[Bias, fairness & safety · 2 works](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2025** 1 paper Josef Dai's papers of 2025](https://md.research.elamur.ai/free/en/papers/ji-2025-pku-saferlhf-multi-level-safety/) · [**2023** 1 paper Josef Dai's papers of 2023](https://md.research.elamur.ai/free/en/papers/dai-2023-safe-rlhf-safe-reinforcement-learning/) ## Papers The most cited first (OpenAlex and our library). 1. **[Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://md.research.elamur.ai/free/en/papers/dai-2023-safe-rlhf-safe-reinforcement-learning/)** *(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](https://md.research.elamur.ai/free/en/papers/ji-2025-pku-saferlhf-multi-level-safety/)** *(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. - [Jiaming Ji](https://md.research.elamur.ai/free/en/authors/jiaming-ji/) ×2 - [Borong Zhang](https://md.research.elamur.ai/free/en/authors/borong-zhang/) - [Mickel Liu](https://md.research.elamur.ai/free/en/authors/mickel-liu/) - [Ruiyang Sun](https://md.research.elamur.ai/free/en/authors/ruiyang-sun/) - [Xuehai Pan](https://md.research.elamur.ai/free/en/authors/xuehai-pan/) - [Yaodong Yang](https://md.research.elamur.ai/free/en/authors/yaodong-yang/) - [Yizhou Wang](https://md.research.elamur.ai/free/en/authors/yizhou-wang/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/): [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) ## 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 →](https://md.research.elamur.ai/free/en/authors/josef-dai/cited-by/). Updated 24 October 2026