4 papers
SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation
Wen Wang, Jiahua Bao, Tu Yongsiqi +8
We aim to improve model performance in multi-reward reinforcement learning training process. Existing Group reward-Decoupled Normalization Policy Optimization (GDPO) has mitigated…
Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG
Haotian Zhou, Weiran Huang, Siqi Liu +3
Cross-lingual retrieval-augmented generation (RAG) is often deployed in an English-evidence regime, where users query in diverse languages but retrieved passages remain English. In…
Let's reward step by step: Step-Level reward model as the Navigators for Reasoning
Qianli Ma, Haotian Zhou, Tingkai Liu +4
Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback…
DavIR: Data Selection via Implicit Reward for Large Language Models
Haotian Zhou, Tingkai Liu, Qianli Ma +5
We introduce DavIR, a model-based data selection method for post-training Large Language Models. DavIR generalizes Reducible Holdout Loss to core-set selection problem of causal la…