arXiv · 2025 · Preprint

FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management

Xiang Liu, Hong Chen, Xuming Hu, Xiaowen Chu

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close
Date
2025-05-21
Citations
9
arXiv
2505.15347
Cite
@misc{liu2025flowkv,
  title = {FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management},
  author = {Xiang Liu and Hong Chen and Xuming Hu and Xiaowen Chu},
  year = {2025},
  eprint = {2505.15347},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.15347},
}