Papers by Longhui Yu
Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Long-CoT reasoning and reinforcement learning are demonstrating remarkable performance and scalability, however, there is a lack of systematic guidelines for obtaining a better initial policy model. |
| Approach: | They propose a systematic guideline and a novel Re-RFT method to obtain more efficient reasoning patterns from different initial models. |
| Outcome: | The proposed method surpasses DeepSeek-R1-Distill-Qwen-14B model by 4.6%, demonstrating its effectiveness and superiority. |
Speed Up Your Code: Progressive Code Acceleration Through Bidirectional Tree Editing (2025.acl-long)
Copied to clipboard
Longhui Zhang, Jiahao Wang, Meishan Zhang, GaoXiong Cao, Ensheng Shi, Mayuchi Mayuchi, Jun Yu, Honghai Liu, Jing Li, Min Zhang
| Challenge: | Existing training methods, such as direct instruction fine-tuning, overlook hierarchical relationships among acceleration patterns. |
| Approach: | They propose a new training paradigm that uses bidirectional tree editing and progressive code acceleration learning to improve LLMs’ CA capabilities. |
| Outcome: | The proposed training paradigm outperforms prompt-enhanced GPT-4 and current training-based methods on average across five programming languages. |
Forward-Backward Reasoning in Large Language Models for Mathematical Verification (2024.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments on six standard mathematical data sets and three LLMs show that FOBAR achieves state-of-the-art performance. |
| Approach: | They propose to combine forward and backward reasoning to verify candidate answers . they propose to use a template to mask a number and ask the LLM to answer a backward question . |
| Outcome: | Experiments on mathematical data show that proposed backward reasoning outperforms Self-Consistency. |