TY - GEN
T1 - Investigating ChatGPT Translation Hallucination from an Embodied-Cognitive Translatology Perspective
AU - Jiao, Hui
AU - Li, Xinwei
AU - Ding, Jonathan
AU - Zhang, Xiaojun
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - ChatGPT faces significant challenges in realising the dynamic construction of reality, cognition and language emphasised in Embodied-cognitive translatology. This study first examines the translation application of ChatGPT, defines hallucination phenomena, and reviews related research. It then explores the hallucination phenomena in ChatGPT’s translation tasks, categorizing them into semantic, pragmatic, syntactic, and cultural hallucinations. To quantify these manifestations, we manually annotate ChatGPT’s English-Chinese translations on the Flores-101 dataset, providing statistical insights into the frequency and severity of each type of hallucination. This analysis offers clarity on the prevalence of various hallucinations and suggests directions for improvement. Finally, this study summarises the current research on hallucination mitigation strategies in a targeted way, including the improvement of corpus quality, model architecture development, and prompt engineering techniques, offering novel insights for advancing machine translation technology towards greater intelligence.
AB - ChatGPT faces significant challenges in realising the dynamic construction of reality, cognition and language emphasised in Embodied-cognitive translatology. This study first examines the translation application of ChatGPT, defines hallucination phenomena, and reviews related research. It then explores the hallucination phenomena in ChatGPT’s translation tasks, categorizing them into semantic, pragmatic, syntactic, and cultural hallucinations. To quantify these manifestations, we manually annotate ChatGPT’s English-Chinese translations on the Flores-101 dataset, providing statistical insights into the frequency and severity of each type of hallucination. This analysis offers clarity on the prevalence of various hallucinations and suggests directions for improvement. Finally, this study summarises the current research on hallucination mitigation strategies in a targeted way, including the improvement of corpus quality, model architecture development, and prompt engineering techniques, offering novel insights for advancing machine translation technology towards greater intelligence.
KW - ChatGPT
KW - Embodied-cognitive translatology
KW - Hallucination
KW - Translation
UR - http://www.scopus.com/inward/record.url?scp=105001028078&partnerID=8YFLogxK
U2 - 10.1007/978-981-96-2885-8_12
DO - 10.1007/978-981-96-2885-8_12
M3 - Conference Proceeding
AN - SCOPUS:105001028078
SN - 9789819628841
T3 - Lecture Notes in Computer Science
SP - 117
EP - 126
BT - Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings
A2 - Hussain, Amir
A2 - Jiang, Bo
A2 - Ren, Jinchang
A2 - Mahmud, Mufti
A2 - Yang, Erfu
A2 - Zheng, Aihua
A2 - Li, Chenglong
A2 - Wang, Shuqiang
A2 - Gao, Zhi
A2 - Zhao, Zhicheng
PB - Springer Science and Business Media Deutschland GmbH
T2 - 14th International Conference on Brain Inspired Cognitive Systems, BICS 2024
Y2 - 6 December 2024 through 8 December 2024
ER -