Saved in:
Bibliographic Details
Main Authors: Lanchantin, Jack, Chen, Angelica, Lan, Janice, Li, Xian, Saha, Swarnadeep, Wang, Tianlu, Xu, Jing, Yu, Ping, Yuan, Weizhe, Weston, Jason E, Sukhbaatar, Sainbayar, Kulikov, Ilia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21495
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We investigate the effectiveness of reinforcement learning methods for finetuning large language models when transitioning from offline to semi-online to fully online regimes for both verifiable and non-verifiable tasks. Our experiments cover training on verifiable math as well as non-verifiable instruction following with a set of benchmark evaluations for both. Across these settings, we extensively compare online and semi-online Direct Preference Optimization and Group Reward Policy Optimization objectives, and surprisingly find similar performance and convergence between these variants, which all strongly outperform offline methods. We provide a detailed analysis of the training dynamics and hyperparameter selection strategies to achieve optimal results. Finally, we show that multi-tasking with verifiable and non-verifiable rewards jointly yields improved performance across both task types.