Knowledge graph triples capture 2-3x more attention per token than equivalent natural language due to structural patterns, compressing demonstration attention by up to 42% independent of semantic relevance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content
Knowledge graph triples capture 2-3x more attention per token than equivalent natural language due to structural patterns, compressing demonstration attention by up to 42% independent of semantic relevance.