2 papers
cs.CL2025
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL
Hanbing Liu, Haoyang Li, Xiaokang Zhang +5
Direct Preference Optimization (DPO) has proven effective in complex reasoning tasks like math word problems and code generation. However, when applied to Text-to-SQL datasets, it…
cs.CL2025
Dynamic Scaling of Unit Tests for Code Reward Modeling
Zeyao Ma, Xiaokang Zhang, Jing Zhang +3
Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this…