1 citations · 2 across the 11 of their papers we have counts for
12 papers
GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation
Kaichen Zhang, Yuzhong Hong, Junwei Bao +4
Post-training plays a pivotal role in enhancing the reasoning capabilities and task-specific expertise of large language models (LLMs). Despite recent advances in post-training met…
PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks
Yuyao Zheng, Haipeng Sun, Junwei Bao +4
Group-based reinforcement learning (RL) has become an effective paradigm for LLM post-training, but in multi-turn agentic tasks with sparse terminal rewards, it often provides coar…
FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning
Haihui Pan, Junwei Bao, Hongfei Jiang +1
While large language models have made significant progress in mathematical reasoning, they remain unreliable at judging the correctness of their own solutions. Existing approaches…
Elo-Evolve: A Co-evolutionary Framework for Language Model Alignment
Jing Zhao, Ting Zhen, Junwei Bao +2
Current alignment methods for Large Language Models (LLMs) rely on compressing vast amounts of human preference data into static, absolute reward functions, leading to data scarcit…
Quality-constrained Entropy Maximization Policy Optimization for LLM Diversity
Haihui Pan, Yuzhong Hong, Kaichen Zhang +4
In many large language model (LLM) alignment applications, users expect not only high-quality outputs but also substantial diversity. However, existing methods often face a fundame…
RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models
Kaichen Zhang, Shenghao Gao, Yuzhong Hong +6
Current large language model post-training optimizes a risk-neutral objective that maximizes expected reward, yet evaluation relies heavily on risk-seeking metrics like Pass@k (at…
GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
Kaichen Zhang, Yuzhong Hong, Junwei Bao +4
Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-training technique…
Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
Yuzhong Hong, Hanshan Zhang, Junwei Bao +2
Since the debut of DPO, it has been shown that aligning a target LLM with human preferences via the KL-constrained RLHF loss is mathematically equivalent to a special kind of rewar…
Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models
Yuchen Fan, Yuzhong Hong, Qiushi Wang +3
Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tunin…
BoRA: Bi-dimensional Weight-Decomposed Low-Rank Adaptation
Qiushi Wang, Yuchen Fan, Junwei Bao +2
In recent years, Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) have significantly enhanced the adaptability of large-scale pre-trained models. Weig…
Multi-Turn Interactions for Text-to-SQL with Large Language Models
Guanming Xiong, Junwei Bao, Hongfei Jiang +2
This study explores text-to-SQL parsing by leveraging the powerful reasoning capabilities of large language models (LLMs). Despite recent advancements, existing LLM-based methods a…
Uncertainty Sentence Sampling by Virtual Adversarial Perturbation
Hanshan Zhang, Zhen Zhang, Hongfei Jiang +1
Active learning for sentence understanding attempts to reduce the annotation cost by identifying the most informative examples. Common methods for active learning use either uncert…