Jailbreaking attacks exploit the complex and sequential nature of human-LLM interactions to subtly manipulate the model ... Additionally, psychological tactics are used so that the likelihood of ...
This repository contains the accompanying code for the paper titled "Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions". The study focuses on the application and ...
Large language models (LLMs) have revolutionized a wide range of domains. In particular, LLMs have been developed as agents to interact with the world and handle various tasks. With continuous ...