TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation
arXiv:2603.03298v1 Announce Type: cross Abstract: Large Language Models (LLMs) have improved substantially alignment, yet their behavior remains highly sensitive to prompt phrasing. This brittleness has …
Bartosz Dziuba, Kacper Kuchta, Pawe{\l} Batorski, Przemys{\l}aw Spurek, Paul Swoboda
25 views