Benchmarking prompt sensitivity in large language models

Amirhossein Razavi, Mina Soltangheis, Negar Arabzadeh, Sara Salamat, Morteza Zihayat, Ebrahim Bagheri
January 2025

Abstract

This paper presents benchmarking approaches for prompt sensitivity in large language models, improving understanding of model behavior and robustness.

Type
Conference paper
Publication
European Conference on Information Retrieval

This work benchmarks prompt sensitivity in large language models for improved understanding.

Large Language Models Prompt Sensitivity Benchmarking Model Robustness Information Retrieval
Morteza Zihayat
Morteza Zihayat
Principal Investigator

Dr. Morteza Zihayat is an Assistant Professor in the School of Information Technology Management at Toronto Metropolitan University and the Director of the Human-Centered Machine Intelligence Lab.