@article{rlearnerllmbalancinglogicalgroundingandf,
  title = {RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization},
  author = {Qiming Bao and Juho Leinonen and Paul Denny and Michael J. Witbrock},
  year = {2026},
  eprint = {2605.04539},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.04539},
}