What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs

Annual Meeting of the Association for Computational Linguistics (ACL), 2025

26 May 2025

Papers citing "What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs"

1 / 1 papers shown

Title
In-Context Learning with Long-Context Models: An In-Depth Exploration Amanda Bertsch Maor Ivgi Uri Alon Jonathan Berant Matthew R. Gormley Matthew R. Gormley Graham Neubig ReLM AIMat 562 112 0 30 Apr 2024