Showing cs.CLShow all
3 papers · 1 filter
cs.CL2025
Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
Huimin Xu, Xin Mao, Feng-Lin Li +4
Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning. Existing approaches, such as Step-DPO, typically improve this by focusing on the first…
cs.CL2024
As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
Xin Mao, Feng-Lin Li, Huimin Xu +3
Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimizat…
cs.CL2024
Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration
Xin Mao, Feng-Lin Li, Huimin Xu +2
While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding…