4 papers
SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter
Powei Chang, Jinpeng Zhang, Chaoqun Sun +6
Reinforcement learning with verifiable rewards (RLVR) often adopts GRPO-style group-relative updates, sampling multiple rollouts per prompt to construct normalized learning signals…
SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training
Powei Chang, Jinpeng Zhang, Bowen Chen +9
Information-based data selection for instruction tuning is compelling: maximizing the log-determinant of the Fisher information yields a monotone submodular objective, enabling gre…
DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space
Jianxiang Xiang, Zhenhua Liu, Haodong Liu +3
In real-life conversations, the content is diverse, and there exists the one-to-many problem that requires diverse generation. Previous studies attempted to introduce discrete or G…
Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generation
Zhenhua Liu, Tong Zhu, Jianxiang Xiang +1
Data augmentation (DA) is crucial to mitigate model training instability and over-fitting problems in low-resource open-domain dialogue generation. However, traditional DA methods…