Elamur Research⌕
☰
home / authors / An Zhang

An Zhang

An Zhang has 6 papers in our library, in 2025, most of them on Language models & pretraining, Bias, fairness & safety, Dialogue systems; often with Tat-Seng Chua, Yang Deng, Bing Qin.

6 papers in our library · 2025

OpenAlex · ORCID · Wikidata · h-index 31 · 245 works · 3,782 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 92 times in our library · ⭐ Paper Stars ranking: #6616

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

🔬Institute of Geographic Sciences and Natural Resources ResearchBeijing · China2005–2026 · 54 papersEducation 2005–2008Employment 2008–2018Employment since 2018current🏛️Chinese Academy of SciencesBeijing · China2006–2026 · 49 paperscurrent🔬State Key Laboratory of Resources and Environmental Information SystemBeijing2011–2026 · 30 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2008–2026 · 9 paperscurrent🎓Tsinghua UniversityBeijing · China2020–2026 · 5 paperscurrent🎓Beihang UniversityBeijing · China2022–2026 · 4 paperscurrent🎓Jinan UniversityGuangzhou · China2025–2026 · 4 paperscurrent🏥ShenZhen People’s HospitalShenzhen · China2025–2026 · 4 paperscurrent🎓Chongqing UniversityChongqing · China2022–2026 · 3 paperscurrent🎓Nanjing University of Aeronautics and AstronauticsNanjing · China2019–2026 · 3 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 68 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 8The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 6 worksComputer Science · 6 worksArtificial Intelligence · 6 worksLanguage and Linguistics · 6 worksComputer Vision and Pattern Recognition · 2 worksInformation Systems · 1 workSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 6Research subjects and languages the work is about.Dialogue systems · 1 workLanguage models & pretraining · 3 worksBias, fairness & safety · 3 worksInformation retrieval & search · 1 workReasoning · 1 workMultilingual & cross-lingual NLP · 1 work

 Works by year

2020s

20256 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Hello Again! LLM-powered Personalized Agent for Long-term Dialogue (2025 · 55 citations)
    Most open-domain chatbots are built for short, single-session exchanges. Real companionship, however, requires remembering past conversations and keeping track of who the user and the bot are. The authors present LD-Agent, a model-agnostic framework that splits long-term dialogue into three separately trainable…
  2. Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning (2025 · 18 citations)
    Retrieval-augmented LLMs trained with reinforcement learning tend to reason over whole retrieved documents, which are often noisy.
  3. Neuron-Level Sequential Editing for Large Language Models (2025 · 15 citations)
    Large language models store facts that go out of date, and full retraining is expensive. Parameter-editing methods such as ROME and MEMIT work well for a single round of edits. When edits are applied one after another, however, they tend to lose earlier edits ("model forgetting") and can collapse into incoherent…
  4. AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025 · 11 citations)
    Safety-aligned LLMs can still be jailbroken. Activation steering is a training-free defense that pushes hidden states toward refusal, but it applies one fixed strength to every input. That fixed setting under-protects against some attacks and causes more false refusals of harmless requests. AdaSteer makes the…
  5. Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025 · 9 citations)
    The paper examines how fine-tuning LLMs for character role-play affects their safety. The authors fine-tuned LLaMA-3-8B-Instruct separately for each of 95 characters from RoleBench. Role-play quality improved, but the models refused harmful AdvBench requests much less often, and villainous characters lost the most…
  6. MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025 · 7 citations)
    Safety-tuned LLMs refuse harmful requests reliably in English but much less so in lower-resource languages.

 Co-authors here

12 of 21 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 92 times (of the 149,439 papers whose bibliographies we read); 25 citing papers with a page here →.

Updated

↑ back to top

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