🧑‍🔬 Muhan Zhang

🏛️ Affiliations

🏛️Jiangsu Academy of Agricultural SciencesNanjing · China2012–2026 · 62 paperscurrent🎓Peking UniversityBeijing · China2022–2026 · 22 paperscurrent🏛️Ministry of Agriculture and Rural AffairsBeijing · China2022–2026 · 8 paperscurrent🎓Jiangsu UniversityZhenjiang · China2021–2026 · 3 paperscurrent🎓Emory UniversityAtlanta · United States2026 · 1 papercurrent🎓University of Science and Technology of ChinaHefei · China2026 · 1 papercurrent🎓Washington University in St. LouisSt Louis · United States2016–2019 · 10 papers🎓Central South UniversityChangsha · China2019–2022 · 7 papers🏛️Beijing Institute for General Artificial IntelligenceBeijing · China2022–2024 · 6 papers🎓Huazhong University of Science and TechnologyWuhan · China2022–2023 · 5 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 15 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. LooGLE: Can Long-Context Language Models Understand Long Contexts? (2023 · 165 citations)
   Existing long-context benchmarks tend to use texts much shorter than current LLM context windows. They also recycle older documents that models may have seen during pre-training, and they mostly test whether a model can find an answer in a single passage. LooGLE addresses these gaps with 776 documents published after…
2. Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners (2023 · 52 citations)
   This work asks where the apparent few-shot reasoning skill of LLMs actually comes from. The authors argue that it depends largely on token meanings absorbed during pretraining, which let models link concepts into shallow shortcut chains instead of applying rules formally. To test this, they remove or invert semantics…
3. Law in Silico: Simulating Legal Society with LLM-Based Agents (2026 · 2 citations)
   Testing legal theories or policies in the real world is often expensive or impossible. This paper asks whether LLM-driven agents can act as a stand-in "legal society" for such experiments. The authors build Law in Silico, a framework with three parts. Agents get hierarchical profiles drawn from sociological…
4. Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation (2026)
   LLMs cannot absorb information that appears after their training cutoff. Supervised fine-tuning (SFT) on new documents can store the facts, but the model often still fails to use them when answering questions or acting as an agent. Reinforcement learning (RL) teaches that kind of skill, yet it is too costly to rerun…

🤝 Co-authors here

7 co-authors with a page, the most papers together first.

• Fanxu Meng ×2
• Jiaqi Li ×2
• Yiding Wang ×2
• Zilong Zheng ×2
• Song-Chun Zhu
• Yitao Liang
• Yuxuan Chen

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) ×2: ACL 2026, ACL 2023
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 151 times (of the 149,439 papers whose bibliographies we read); 31 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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