Skip to search boxSkip to navigationSkip to main content

Provoking unstable and evasive ChatGPT behaviour with anti-chain-of-thought: Japanese rock song lyrics case, a year later

Research Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
 Peer-review

Open access

Abstract

Considerably attention has been directed towards assessing the capabilities of ChatGPT and other Large Language Models (LLMs) in various aspects such as syntax accuracy, factual correctness, comprehensive world understanding, ethical alignment, common sense, and formal logical reasoning. However, the bulk of the research has primarily focused on analyzing "statically"generated texts, where only a single interaction between a human and LLMs was documented. More sophisticated methodologies involving open-ended discussions or debates between humans and LLMs yield far more intriguing outcomes. These reveal flawed rhetorical patterns, including circular arguments, self-contradictions, topic evasion, inconsistency, and a blend of passive aggression with attempts to please the human disputant. In this paper, we present an original observation of such behaviour occurring during a ChatGPT dialogue session centred around the translation of Japanese song lyrics.

Publication Information

Output type

Research Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
 Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 207-215 (9 pages)

Publication milestones

  • Published - 28/01/2025

Publication status

Published - 28/01/2025

Publisher

Institute of Electrical and Electronics Engineers Inc., United States

Publication series

  • Publication series name: 2024 2nd International Conference on Foundation and Large Language Models (FLLM)

ISBN (Print)

9798350354799

ISBN (Electronic)

9798350354799

Publication IDs

  • handle.net: 10547/626855
  • Scopus: 85218344284

Host publication title

2024 2nd International Conference on Foundation and Large Language Models, FLLM 2024

Host publication editors

  • Yaser Jararweh
  • Jim Jansen
  • Mohammad Alsmirat

Access to documents

Publication metrics