🧑‍🔬 Zhongyuan Peng

🏛️ Affiliations

🎓Fudan UniversityShanghai · China2026 · 2 paperscurrent🏢MeituanBeijing · China2026 · 1 papercurrent🎓University of Chinese Academy of SciencesBeijing · China2023–2025 · 5 papers🎓Shanghai Jiao Tong UniversityShanghai · China2021 · 5 papers🏛️Chinese Academy of SciencesBeijing · China2023–2025 · 3 papers🏢Alibaba GroupHangzhou · China2024–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution 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. RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (2023 · 187 citations)
   Open-source LLMs are trained for general use and are weak at imitating specific fictional characters. Strong closed models such as GPT-4 can do this, but they are costly, cannot be fine-tuned, and need all character details placed in the prompt. RoleLLM addresses this with a four-stage pipeline. First, the authors…
2. Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025 · 30 citations)
   Reasoning models in the o1 style produce very long chains of thought (CoT). Until this paper, there was no systematic way to check how good those chains are, or whether other models can find the mistakes in them. The authors built DeltaBench to address both gaps. It contains 1,236 problems from Math, Programming, PCB…
3. CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization (2026 · 12 citations)
   Turning informal math problems into Lean 4 theorem statements often produces code that compiles but does not mean what the original problem says.
4. SCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning (2026 · 2 citations)
   RL post-training for LLM reasoning tends to stall for two reasons. Tasks can drift out of step with the model, becoming either trivially easy or hopelessly hard, so rewards turn sparse. Training can also keep cycling through a small set of problem patterns. SCALER tackles both issues. Its first part is a synthesis…

All works

7 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. RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language ModelsarXiv:2310.00746Zekun Moore Wang, Zhongyuan Peng, Haoran Que, et al.2023 · 187 citations
2. RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models ↗Findings of the Association for Computational Linguistics: ACL 2024 · no summary yetNoah Wang et al.2024 · 114 citations
3. SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines ↗arXiv:2502.14739 · no summary yetM-A-P Team et al.2025 · 89 citations
4. FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models ↗arXiv:2505.02735 · no summary yetZhouliang Yu et al.2025 · 31 citations
5. Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?Annual Meeting of the Association for Computational Linguistics (ACL)Yancheng He, Shilong Li, Jiaheng Liu, et al.2025 · 30 citations
6. CriticLean: Critic-Guided Reinforcement Learning for Mathematical FormalizationAnnual Meeting of the Association for Computational Linguistics (ACL)Zhongyuan Peng, Yifan Yao, Kaijing Ma, et al.2026 · 12 citations
7. SCALER: Synthetic Scalable Adaptive Learning Environment for ReasoningFindings of the Association for Computational LinguisticsCaijun Xu, Changyi Xiao, Zhongyuan Peng, et al.2026 · 2 citations

🤝 Co-authors here

12 of 22 co-authors with a page, the most papers together first.

• Jiaheng Liu ×2
• Zhaoxiang Zhang ×2
• Bo Zheng
• Chenchen Zhang
• Ge Zhang
• Haoran Que
• Jian Yang
• Man Zhang
• Shilong Li
• Shuyue Guo
• Wangchunshu Zhou
• Weixun Wang

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 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Findings of the Association for Computational Linguistics: ACL 2024

🔗 Cited by

Papers of our library cite their works 338 times (of the 149,439 papers whose bibliographies we read); 88 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/zhongyuan-peng/