Why large language models cannot possess consciousness: an integrated information theory perspective
Current LLMs do not satisfy the structural and informational requirements of consciousness under IIT. Although capable of simulating intelligent language, LLMs remain unconscious systems with a negligible amount of integrated information, underscoring the distinction between linguistic competence and conscious experience.
Authors
- Dong Ah Shin (ORCID: https://orcid.org/0000-0002-5225-4083)
- Pyung Goo Cho
- Sungwoo Kim (ORCID: https://orcid.org/0000-0002-5392-1060)
- Min Cheol Chang (ORCID: https://orcid.org/0000-0002-7629-7213)
- S Park (ORCID: https://orcid.org/0000-0003-0476-2355)
- Yoo Jin Choo
- Gyu Yeul Ji
Institutions
- Yonsei University (KR)
- Severance Hospital (KR)
- Ajou University Hospital (KR)
- Yeungnam University College
- Yeungnam University (KR)
Publication Details
- Journal
- Journal of Yeungnam Medical Science
- Published
- 2025-12-01
- DOI
- https://doi.org/10.12701/jyms.2025.42.79
- Primary Topic
- Neurobiology of Language and Bilingualism
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Yeungnam University