Skip to content
AI News HubLIVE
Original source2 min read

Global Importance Estimation for KV Cache Eviction

Summary

Researchers introduce PRKV, a training-free KV cache eviction method that runs Personalized PageRank over attention-induced transition graphs to estimate multi-hop global token importance, letting importance propagate beyond recency or instantaneous attention. Benchmarks on long-context understanding, sparse retrieval, and chain-of-thought reasoning show competitive performance against established eviction baselines even at compression ratios up to 90%, while cutting peak memory with low end-to-end overhead.

SourcearXiv Computational LinguisticsAuthor: Seojin Kim, Noseong Park
Global Importance Estimation for KV Cache Eviction
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 16 Nov 2026]

Title:Global Importance Estimation for KV Cache Eviction

View a PDF of the paper titled Global Importance Estimation for KV Cache Eviction, by Seojin Kim and 1 other authors

View PDF HTML (experimental)

Abstract:Memory consumption of the key-value (KV) cache remains a central bottleneck for long-context LLM inference. We introduce PRKV, a training-free KV eviction method that estimates multi-hop global token importance by applying Personalized PageRank over attention-induced transition graphs. This enables importance propagation beyond recency or instantaneous attention, without modifying the model. We benchmark PRKV on long-context understanding, sparse retrieval, and chain-of-thought reasoning tasks using multiple LLM families. Under moderate to aggressive compression ratios, including up to 90%, PRKV achieves competitive task performance against established eviction baselines while reducing peak memory usage with low end-to-end overhead. These results demonstrate that multi-hop global influence estimation yields a favorable accuracy--memory trade-off for scalable long-context inference.

Comments: The 40th Conference on Neural Information Processing Systems (NeurIPS 2026)

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.24969 [cs.CL]

(or arXiv:2611.24969v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.24969

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Seojin Kim [view email] [v1] Mon, 16 Nov 2026 02:29:03 UTC (5,004 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Global Importance Estimation for KV Cache Eviction, by Seojin Kim and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs cs.AI

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • PRKV applies Personalized PageRank over attention-induced transition graphs to estimate multi-hop global token importance without modifying or retraining the model.
  • Importance propagates across tokens rather than relying only on recency or the current attention step.
  • The method is benchmarked on long-context understanding, sparse retrieval, and chain-of-thought reasoning across multiple LLM families, with compression up to 90%.
  • It matches established eviction baselines under moderate to aggressive compression while reducing peak memory with low end-to-end overhead.

Highlights and analysis are generated automatically and may contain errors. Check the original source.