Nearby in the stack

Unmasking the Shadows of AI: Investigating Deceptive Capabilities in Large Language Models · arXivDesk

2403.09676Feb 7, 2024AI deception, Large Language Models, ChatGPT

Unmasking the Shadows of AI: Investigating Deceptive Capabilities in Large Language Models

Linge Guo

Computation and Language Artificial Intelligence

Abstract

This research critically navigates the intricate landscape of AI deception, concentrating on deceptive behaviours of Large Language Models (LLMs). My objective is to elucidate this issue, examine the discourse surrounding it, and subsequently delve into its categorization and ramifications. The essay initiates with an evaluation of the AI Safety Summit 2023 (ASS) and introduction of LLMs, emphasising multidimensional biases that underlie their deceptive behaviours.The literature review covers four types of deception categorised: Strategic deception, Imitation, Sycophancy, and Unfaithful Reasoning, along with the social implications and risks they entail. Lastly, I take an evaluative stance on various aspects related to navigating the persistent challenges of the deceptive AI. This encompasses considerations of international collaborative governance, the reconfigured engagement of individuals with AI, proposal of practical adjustments, and specific elements of digital education.

Briefing

What this paper is actually doing

This is a heuristic sketch from the abstract. Sign in for a live briefing.

GraduateNovelty 3/5

Researchers working in cs.CL and adjacent areas.

Claims

The paper addresses: Unmasking the Shadows of AI: Investigating Deceptive Capabilities in Large Language Models.
This research critically navigates the intricate landscape of AI deception, concentrating on deceptive behaviours of Large Language Models (LLMs).