2 papers
cs.CR2025
LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
Sahar Abdelnabi, Aideen Fay, Ahmed Salem +22
Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous def…
cs.CL2024
Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling
Yao-Ching Yu, Chun-Chih Kuo, Ziqi Ye +2
Ensembling multiple models has always been an effective approach to push the limits of existing performance and is widely used in classification tasks by simply averaging the class…