Back to Arena

Scissorhands

by Rice / Stanford / Meta (Liu et al.)

System Card

OrganizationRice / Stanford / Meta (Liu et al.)
Released2023-05
Architecturekv-cache-extension / Persistence-of-importance KV pruning
DetailsBased on the "persistence of importance" hypothesis: tokens with high past attention impact remain pivotal for future generations. Maintains a fixed KV budget by storing pivotal tokens with higher probability.
Parameters—
Domainlong-context
Open SourceNo
PaperView Paper
neurips-2023pruningkvquantization-compatible

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Data Transparency:6 estimated
Long-Context Retrieval
5/5
RULER
73.266pEstimated
NIAH
72.223pEstimated
LooGLE
72.918pEstimated
LongBench
603pEstimated
∞Bench
84.584pEstimated
Multi-Turn Recall
0/2
LoCoMo
no data
MemoryBank
no data
Cross-Session Memory
0/1
LongMemEval
no data
Multi-Hop QA
1/3
BABILong
75.651pEstimated
MultiHop-RAG
no data
HotpotQA
no data
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Arena estimate — derived from capability profile, not independently verified