CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
Paper
•
2508.15868
•
Published
•
3
•
3
WNQzhu
Qlisp
AI & ML interests
None yet
Recent Activity
liked
a dataset
1 day ago
google/IFEval
liked
a dataset
1 day ago
allenai/ai2_arc
liked
a dataset
14 days ago
AI4Math/MathVista
Organizations
None yet