🧑‍🔬 Ningyu Zhang

🏛️ Affiliations

🎓Zhejiang UniversityHangzhou · China2013–2026 · 139 papersEmploymentcurrent🎓Nanjing UniversityNanjing · China2024–2026 · 5 paperscurrent🎓Northwestern Polytechnical UniversityXi'an · China2026 · 1 papercurrent🏢Ant GroupHangzhou · China2023–2025 · 22 papers🏢Alibaba GroupHangzhou · China2019–2025 · 14 papers🎓National University of SingaporeSingapore · Singapore2023–2025 · 7 papers🎓University of California, Los AngelesLos Angeles · United States2024–2025 · 3 papers🏢State Grid Jiangsu Electric PowerNanjing · China2021–2022 · 2 papers🔬Zhejiang LabHangzhou · China2018 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 13 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Reasoning with Language Model Prompting: A Survey (2022 · 161 citations)
   This survey maps the fast-growing work on getting large language models to reason through prompting rather than through task-specific architectures.
2. Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View (2024 · 131 citations)
   Systems built from several large language model agents are increasingly used for hard tasks, but it is unclear how their collaboration works or whether it resembles human group behaviour.
3. Detoxifying Large Language Models via Knowledge Editing (2024 · 84 citations)
   Safety-aligned LLMs can still be steered into harmful output when a malicious request is wrapped in a carefully engineered jailbreak prompt. The authors ask whether knowledge editing can fix the specific toxic parts of a model instead of only masking them.
4. CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2021 · 71 citations)
   Biomedical NLP evaluation resources such as BLURB and PubMedQA are almost entirely English. Chinese, spoken by roughly a quarter of humanity, has had no shared yardstick for medical language understanding. The authors address this with CBLUE, which they describe as the first Chinese benchmark of its kind. It combines…

All works

14 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Reasoning with Language Model Prompting: A SurveyShuofei Qiao, Yixin Ou, Ningyu Zhang, et al.arXiv:2212.09597 · 161 citations
2. Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology ViewJintian Zhang, Xin Xu, Ningyu Zhang, et al.Annual Meeting of the Association for… · 131 citations
3. Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models (original ↗)Yin Fang et al.2023 · arXiv:2306.08018 · 89 citations · no summary yet
4. Detoxifying Large Language Models via Knowledge EditingMengru Wang, Ningyu Zhang, Ziwen Xu, et al.Annual Meeting of the Association for… · 84 citations
5. CBLUE: A Chinese Biomedical Language Understanding Evaluation BenchmarkNingyu Zhang, Mosha Chen, Zhen Bi, et al.arXiv:2106.08087 · 71 citations
6. LightThinker: Thinking Step-by-Step Compression (original ↗)Jintian Zhang et al.2025 · Proceedings of the 2025 Conference on Empirical… · 50 citations · no summary yet
7. Symbolic Learning Enables Self-Evolving Agents (original ↗)Wangchunshu Zhou et al.2024 · arXiv:2406.18532 · 32 citations · no summary yet
8. OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking (original ↗)Zekun Xi et al.2025 · Proceedings of the 2025 Conference on Empirical… · 14 citations · no summary yet
9. Can We Predict Before Executing Machine Learning Agents? (original ↗)Jingsheng Zheng et al.2026 · Proceedings of the 64th Annual Meeting of the… · 2 citations · no summary yet
10. Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics (original ↗)Ziwen Xu et al.2026 · Proceedings of the 64th Annual Meeting of the… · 1 citation · no summary yet
11. What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations (original ↗)Yujie Luo et al.2026 · Proceedings of the 64th Annual Meeting of the… · no summary yet
12. U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents (original ↗)Jin Su et al.2026 · Findings of the Association for Computational… · no summary yet
13. How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities (original ↗)Ziwen Xu et al.2026 · Proceedings of the 64th Annual Meeting of the… · no summary yet
14. Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency (original ↗)Haoming Xu et al.2026 · Proceedings of the 64th Annual Meeting of the… · no summary yet

🤝 Co-authors here

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

• Shumin Deng ×3
• Chuanqi Tan ×2
• Fei Huang ×2
• Huajun Chen ×2
• Yunzhi Yao ×2
• Bryan Hooi
• Jindong Wang
• Lei Li
• Linyi Yang
• Luo Si
• Ruibo Liu
• Xin Xu

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… ×7: 2024 ×2
• Proceedings of the 2025 Conference on Empirical Methods in… ×2
• Findings of the Association for Computational Linguistics…

🔗 Cited by

Papers of our library cite their works 472 times (of the 141,840 papers whose bibliographies we read); 27 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

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