LLMs disperse meaning-preserving prompts internally instead of clustering them, which produces an excessively high upper bound on output log-probability differences via Taylor expansion and Cauchy-Schwarz.
Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Understanding the Prompt Sensitivity
LLMs disperse meaning-preserving prompts internally instead of clustering them, which produces an excessively high upper bound on output log-probability differences via Taylor expansion and Cauchy-Schwarz.