KV cache compression can preserve final-answer accuracy while degrading the validity of reasoning chains that support those answers, creating an answer-evidence gap.
H2O: heavy-hitter oracle for efficient generative inference of large language models , year =
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
-
Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression
KV cache compression can preserve final-answer accuracy while degrading the validity of reasoning chains that support those answers, creating an answer-evidence gap.