Papers by Fuwei Cui
An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for constructing process supervision training data are costly or suffer from poor quality. |
| Approach: | They propose a framework called EpicPRM which annotates each intermediate reasoning step based on its quantified contribution and uses an adaptive binary search algorithm to enhance annotation precision and efficiency. |
| Outcome: | The proposed framework improves annotation precision and efficiency and can be used to train a high-quality training dataset with 50k annotated intermediate steps. |
Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing conversation models produce meaningless and generic responses, which significantly reduce the user experience. |
| Approach: | They propose to fuse knowledge to improve informativeness and adopt latent variables to enhance the diversity of responses. |
| Outcome: | The proposed model can generate syntactically diverse and knowledge-accurate responses while maintaining the knowledge accuracy. |