Yongbing Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yongbing Chen has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Boyu Wang
Western University
1 shared publication - Charles X. Ling
Western University
1 shared publication - Dingyi Jiang
Western University London ON Canada
1 shared publication Jiacheng Wu
School of Mechanical Engineering, Jiangsu University, Zhenjiang, China
1 shared publicationJingjing Zhang
School of Mechanical Engineering, Jiangsu University, Zhenjiang, China
1 shared publication- Liping Liu
College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China
1 shared publication
Latest Publications
- 8 December 2025
- Published by Springer Nature in Journal of Materials Engineering and Performance
- Vol. 35 (18) , 18073-18088
High-Temperature Oxidation Behavior of a New Type of Ti-3Al-2V Titanium Alloy at 450 and 750 °C
- 8 December 2025
- Published by Springer Nature in Journal of Materials Engineering and Performance
- Vol. 35 (18) , 18073-18088
High-Temperature Oxidation Behavior of a New Type of Ti-3Al-2V Titanium Alloy at 450 and 750 °C
- Open Access
Enhancing Generalization in Chain of Thought Reasoning for Smaller Models
Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly conservative memorization in smaller LLMs, leading to low generalization confidence. As fully preserving the CoT ability of teacher model is impossible, we hypothesize that adversarial CoT fine-tuning is crucial for developing smaller LLM with robust CoT generalization. To this end, we propose \textit{PRompt-Assisted Domain-Adversarial fine-tuning} (PRADA), a principled fine-tuning framework that integrates diverse CoT domains. Specifically, PRADA pioneers two CoT improvements in smaller LLM: (1) Recovering the domain-invariant feature insight which typically lost during distillation with domain adversarial fine-tuning; (2) Enhancing the domain adaptability of CoT prompt engineering by employing domain-adversarial approaches. We theoretically demonstrate the effectiveness of our approach and empirically show that it significantly outperforms the state of the arts in a wide range of tasks. Moreover, our empirical findings reveal that the smaller LLM, when leveraging PRADA, aligns closely with domain knowledge, thereby improving the explainability of our approach.
Open AccessEnhancing Generalization in Chain of Thought Reasoning for Smaller Models
Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly conservative memorization in smaller LLMs, leading to low generalization confidence. As fully preserving the CoT ability of teacher model is impossible, we hypothesize that adversarial CoT fine-tuning is crucial for developing smaller LLM with robust CoT generalization. To this end, we propose \textit{PRompt-Assisted Domain-Adversarial fine-tuning} (PRADA), a principled fine-tuning framework that integrates diverse CoT domains. Specifically, PRADA pioneers two CoT improvements in smaller LLM: (1) Recovering the domain-invariant feature insight which typically lost during distillation with domain adversarial fine-tuning; (2) Enhancing the domain adaptability of CoT prompt engineering by employing domain-adversarial approaches. We theoretically demonstrate the effectiveness of our approach and empirically show that it significantly outperforms the state of the arts in a wide range of tasks. Moreover, our empirical findings reveal that the smaller LLM, when leveraging PRADA, aligns closely with domain knowledge, thereby improving the explainability of our approach.