@article{carerftconfidenceanchoredreinforcementfi,
  title = {CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models},
  author = {Shuozhe Li and Jincheng Cao and Bodun Hu and Aryan Mokhtari and Leqi Liu and Amy Zhang},
  year = {2026},
  eprint = {2602.00085},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.00085},
}