TY - GEN
T1 - Yet another example of ChatGPT's evasive tactics during long conversations: Japanese rock song lyrics case
AU - Selitskiy, Stanislav
AU - Inoue, Chihiro
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/6/12
Y1 - 2024/6/12
N2 - Much attention has been devoted to the ChatGPT and other Large Language Models’ (LLM) capability assessment regarding syntax correctness, factual accuracy, adequate world representation, ethical alignment, common sense and formal logic reasoning. However, most of the research focused on "statically" generated texts, when the result of only a single iteration between a human and LLMs was recorded. More advanced techniques of open-ended discussions or debates between a human and LLMs produce much more interesting results, demonstrating such faulty rhetorical behaviours as circular arguments, self-contradictions, evasion, change of topic, lack of consistent position, and the mix of passive aggression with attempts to please human disputant. We present an original observation of such behaviour during the ChatGPT dialogue session discussing the translation of Japanese song lyrics.
AB - Much attention has been devoted to the ChatGPT and other Large Language Models’ (LLM) capability assessment regarding syntax correctness, factual accuracy, adequate world representation, ethical alignment, common sense and formal logic reasoning. However, most of the research focused on "statically" generated texts, when the result of only a single iteration between a human and LLMs was recorded. More advanced techniques of open-ended discussions or debates between a human and LLMs produce much more interesting results, demonstrating such faulty rhetorical behaviours as circular arguments, self-contradictions, evasion, change of topic, lack of consistent position, and the mix of passive aggression with attempts to please human disputant. We present an original observation of such behaviour during the ChatGPT dialogue session discussing the translation of Japanese song lyrics.
KW - ChatGPT
KW - ChatGPT evaluation
KW - Large Language Model evasion practices
KW - Large Language Model long discussion
KW - anti-chain-of-thought
KW - chatbots
KW - LLM evasion practices
KW - LLM long discussion
UR - https://www.scopus.com/pages/publications/85196754992
U2 - 10.1109/CogSIMA61085.2024.10554038
DO - 10.1109/CogSIMA61085.2024.10554038
M3 - Conference contribution
SN - 9798350362824
T3 - 2024 IEEE Conference on Cognitive and Computational Aspects of Situation Management, CogSIMA 2024
SP - 132
EP - 136
BT - 2024 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)
Y2 - 7 May 2024 through 10 May 2024
ER -