Implicit Perception of Differences between NLP-Produced and Human-Produced Language in the Mentalizing Network

Zhengde Wei, Ying Chen, Qian Zhao, Pengyu Zhang, Longxi Zhou, Jiecheng Ren, Yi Piao, Bensheng Qiu, Xing Xie, Suiping Wang, Jia Liu, Daren Zhang, Roi Cohen Kadosh, Xiaochu Zhang

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Natural language processing (NLP) is central to the communication with machines and among ourselves, and NLP research field has long sought to produce human-quality language. Identification of informative criteria for measuring NLP-produced language quality will support development of ever-better NLP tools. The authors hypothesize that mentalizing network neural activity may be used to distinguish NLP-produced language from human-produced language, even for cases where human judges cannot subjectively distinguish the language source. Using the social chatbots Google Meena in English and Microsoft XiaoIce in Chinese to generate NLP-produced language, behavioral tests which reveal that variance of personality perceived from chatbot chats is larger than for human chats are conducted, suggesting that chatbot language usage patterns are not stable. Using an identity rating task with functional magnetic resonance imaging, neuroimaging analyses which reveal distinct patterns of brain activity in the mentalizing network including the DMPFC and rTPJ in response to chatbot versus human chats that cannot be distinguished subjectively are conducted. This study illustrates a promising empirical basis for measuring the quality of NLP-produced language: adding a judge's implicit perception as an additional criterion.
Original languageEnglish (US)
Pages (from-to)2203990
JournalAdvanced Science
StatePublished - Feb 7 2023

Bibliographical note

KAUST Repository Item: Exported on 2023-02-10
Acknowledgements: This work was supported by grants from The Chinese National Programs for Brain Science and Brain-like Intelligence Technology (2021ZD0202101), The National Natural Science Foundation of China (71942003, 32161143022, 32171080, and 31900766), Major Project of Philosophy and Social Science Research, Ministry of Education of China (19JZD010), CAS-VPST Silk Road Science Fund 2021 (GLHZ202128), Collaborative Innovation Program of Hefei Science Center, CAS (2020HSC-CIP001), and Anhui Provincial Key Research and Development Project (202004b11020013). The authors thank the Bioinformatics Center of the University of Science and Technology of China, School of Life Science, for providing supercomputing resources for this project.


Dive into the research topics of 'Implicit Perception of Differences between NLP-Produced and Human-Produced Language in the Mentalizing Network'. Together they form a unique fingerprint.

Cite this