Jiacheng Chen
Jiacheng Chen has 2 papers in our library, in 2025, most of them on Language models & pretraining, Reasoning; often with Ganqu Cui, Lifan Yuan, Weize Chen.
OpenAlex · ORCID · h-index 4 · 9 works · 80 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 249 times in our library · ⭐ Paper Stars ranking: #5952
Affiliations
🎓Chinese University of Hong KongHong Kong ·
China2026 · 1 paper🎓South China University of TechnologyGuangzhou ·
China2024 · 2 papers
Fields, topics and concepts
📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works
🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 1 workReasoning · 1 work
Works by year
2020s
Papers
- Process Reinforcement through Implicit Rewards (2025 · 151 citations)
Reinforcement learning for LLM reasoning usually relies on one verifiable reward at the end of each response. - The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models (2025 · 101 citations)
Reinforcement learning with verifiable rewards is now a main way to improve LLM reasoning, but scaling it hits a recurring problem. Without explicit regularization, policy entropy falls to almost zero within the first training steps. The model becomes overconfident, stops exploring and its validation accuracy stalls.
Co-authors here
- Ganqu Cui ×2
- Lifan Yuan ×2
- Weize Chen ×2
- Yuchen Fan ×2
- Yuchen Zhang ×2
- Bingxiang He
- Hanbin Wang
- Hao Peng
- Haozhan Li
- Huayu Chen
- Tianyu Yu
- Wendi Li
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/jiacheng-chen/