Elamur Research⌕
☰
home / authors / Han Zhao

Han Zhao

Han Zhao has 2 papers in our library, in 2024, most of them on Language models & pretraining; often with Haoxiang Wang, Tong Zhang, Wei Xiong.

2 papers in our library · 2024

OpenAlex · ORCID · h-index 13 · 56 works · 751 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 184 times in our library · ⭐ Paper Stars ranking: #4625

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

🏥Beijing Tongren HospitalBeijing · China2026 · 1 papercurrent🎓Capital Medical UniversityBeijing · China2026 · 1 papercurrent🎓City University of Hong KongHong Kong · Hong Kong2022–2025 · 9 papers🎓University of Illinois Urbana-ChampaignUrbana · United States2021–2025 · 7 papers🎓Shanghai Jiao Tong UniversityShanghai · China2020–2024 · 5 papers🎓Jilin UniversityChangchun · China2020–2025 · 3 papers🔬State Key Laboratory of Mechanical System and VibrationShanghai2020–2022 · 3 papers🎓Soochow UniversitySuzhou · China2024–2025 · 2 papers🎓Nanjing University of Chinese MedicineNanjing · China2023–2024 · 2 papers🏥Ruijin HospitalShanghai · China2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 22 more institutions 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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksInformation Systems · 1 work

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 1 work

 Works by year

2020s

20242 papersHan Zhao's papers of 2024

 Papers

The most cited first (OpenAlex and our library).

  1. Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts (2024 · 142 citations)
    Reward models (RMs) in RLHF usually learn from binary pairwise preferences with a Bradley-Terry objective.
  2. Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024 · 66 citations)
    Standard RLHF compresses human judgments into one scalar reward. This pushes a model toward an "average user" and ignores people whose tastes conflict, such as those who want useful but short answers. The authors propose Directional Preference Alignment (DPA) to address this.

 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 184 times (of the 141,840 papers whose bibliographies we read); 8 citing papers with a page here →.

Updated

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