6 papers
ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
Tianjian Liu, Fanqi Wan, Jiajian Guo +1
Proactive dialogue has emerged as a critical and challenging research problem in advancing large language models (LLMs). Existing works predominantly focus on domain-specific or ta…
Mutual-Taught for Co-adapting Policy and Reward Models
Tianyuan Shi, Canbin Huang, Fanqi Wan +5
During the preference optimization of large language models (LLMs), distribution shifts may arise between newly generated model samples and the data used to train the reward model…
FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion
Longguang Zhong, Fanqi Wan, Ziyi Yang +3
Heterogeneous model fusion enhances the performance of LLMs by integrating the knowledge and capabilities of multiple structurally diverse models. However, existing approaches ofte…
FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion
Ziyi Yang, Fanqi Wan, Longguang Zhong +3
We introduce FuseChat-3.0, a suite of large language models (LLMs) developed by integrating the strengths of heterogeneous source LLMs into more compact target LLMs. Our source mod…
Advantage-Guided Distillation for Preference Alignment in Small Language Models
Shiping Gao, Fanqi Wan, Jiajian Guo +2
Alignment techniques enable Large Language Models (LLMs) to generate outputs that align with human preferences and play a crucial role in their effectiveness. However, their impact…
Weighted-Reward Preference Optimization for Implicit Model Fusion
Ziyi Yang, Fanqi Wan, Longguang Zhong +2
While fusing heterogeneous open-source LLMs with varying architectures and sizes can potentially integrate the strengths of different models, existing fusion methods face significa…