Input compression increases net cost and reduces accuracy as models respond longer; output compression reduces cost on most models, with surface text diverging from unconstrained references on non-reasoning models.
Positional Encoding to Control Output Sequence Length
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression
Input compression increases net cost and reduces accuracy as models respond longer; output compression reduces cost on most models, with surface text diverging from unconstrained references on non-reasoning models.