🧑‍🔬 Weixiang Zhao

🏛️ Affiliations

🎓Soochow UniversitySuzhou · China2018–2026 · 2 paperscurrent🎓University of California, DavisDavis · United States2007–2015 · 29 papers🎓Harbin Institute of TechnologyHarbin · China2021–2025 · 17 papers🎓Clarkson UniversityPotsdam · United States2004–2009 · 14 papers🎓Zhejiang UniversityHangzhou · China1998–2004 · 4 papers🎓Sun Yat-sen UniversityGuangzhou · China2024–2025 · 3 papers🏢National GridNew York · United States2012–2014 · 3 papers🎓Anhui Medical UniversityHefei · China2024 · 2 papers🎓Northeastern UniversityShenyang · China2020 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. 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…
2. 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…
3. 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.
4. On Safety Risks in Experience-Driven Self-Evolving Agents (2026 · 1 citation)
   Experience-driven self-evolving LLM agents improve by distilling lessons from past interactions into an external memory and retrieving them for new tasks, while model weights stay frozen.
5. TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent (2026 · 1 citation)
   Most emotional support conversation (ESC) systems and benchmarks only measure empathetic wording in text-only settings.

🤝 Co-authors here

12 of 14 co-authors with a page, the most papers together first.

• Bing Qin ×5
• Yanyan Zhao ×5
• Jiahe Guo ×4
• Ting Liu ×4
• Yang Deng ×4
• Yulin Hu ×4
• An Zhang ×3
• Tat-Seng Chua ×3
• Xingyu Sui ×3
• Xinyang Han ×2
• Hao He
• Tongtong Wu

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) ×3: ACL 2026, ACL 2025 ×2
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 27 times (of the 149,439 papers whose bibliographies we read); 8 citing papers with a page here →.

Updated 31 October 2026

↑ back to top

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