PatchKV: Efficient KV Cache Recovery for Dynamically Edited LLM Contexts

arXiv:2609.26219 · cs.DC, cs.LG · Submitted 2026-08-18 · Read on arXiv

cs.DC, cs.LG

Submitted: 2026-08-18

Updated: 2026-08-18

Comments: 10 pages, 10 figures, 2 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

F1 Score — 21× in this paper · explained in 3 episodes
KV cache — 19× in this paper · explained in 3 episodes
Calibration — 9× in this paper · explained in 7 episodes
Quantization — 8× in this paper · explained in 12 episodes
Decode — 6× in this paper · explained in 2 episodes
Transformer — 5× in this paper · explained in 2 episodes
Ablation — 4× in this paper · explained in 1 episode
RAG — 4× in this paper · explained in 3 episodes
Aggregation — 2× in this paper · explained in 1 episode
Alignment — 2× in this paper · explained in 1 episode
KV cache reuse — 2× in this paper · explained in 2 episodes
Trace — 2× in this paper · explained in 2 episodes
Benchmark — 1× in this paper · explained in 2 episodes
Cosine Similarity — 1× in this paper · explained in 3 episodes
Generative Model — 1× in this paper · explained in 2 episodes
Generative Models — 1× in this paper · explained in 2 episodes
Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
Reconstruction Error — 1× in this paper · explained in 2 episodes
Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
Sparse Attention — 1× in this paper · explained in 5 episodes