Black-box Optimization of LLM Outputs by Asking for Directions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Jie, Ding, Meng, Liu, Yang, Hong, Jue, Tramèr, Florian
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.16794