5 papers
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
Dylan Zhang, Yufeng Xu, Haojin Wang +2
Post-training of reasoning LLMs is a holistic process that typically consists of an offline SFT stage followed by an online reinforcement learning (RL) stage. However, SFT is often…
D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancement
Bin Liu, Haoyu Peng, Zhijia Wei +2
Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch selection methods typically re…
The Best Instruction-Tuning Data are Those That Fit
Dylan Zhang, Qirun Dai, Hao Peng
High-quality supervised fine-tuning (SFT) data are crucial for eliciting strong capabilities from pretrained large language models (LLMs). Typically, instructions are paired with m…
Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
Qirun Dai, Dylan Zhang, Jiaqi W. Ma +1
Selecting appropriate training data is crucial for instruction fine-tuning of large language models (LLMs), which aims to (1) elicit strong capabilities, and (2) achieve balanced p…
: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
Dylan Zhang, Shizhe Diao, Xueyan Zou +1
Preference learning provides a promising solution to address the limitations of supervised fine-tuning (SFT) for code language models, where the model is not explicitly trained to…