Haipang Wu

CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

Reasoning capability plays a significantly critical role in the the broad applications of Large Language Models (LLMs). To enhance the reasoning performance of LLMs, diverse Reinforcement Learning (RL)-based fine-tuning approaches have been proposed to address the limited generalization capability o