@article{sentencekvefficientllminferencevia,
  title = {SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching},
  author = {Yuxuan Zhu and Ali Falahati and David H. Yang and Mohammad Mohammadi Amiri},
  year = {2025},
  eprint = {2504.00970},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.00970v1},
}