A clarification of the conditions under which Large ... • …

A clarification of the conditions under which Large ...

• Large Language Models (LLMs) are rapidly transforming society, raising public concerns about their potential consciousness.
• Public discourse is filled with questions about LLM consciousness, but scientific disagreement on consciousness makes concrete answers contentious.
• This paper explores the possibility of LLM consciousness, offering a temporary guide for theorizing about it.
• LLMs are advanced neural networks trained on vast amounts of internet text, simulating natural language interactions with humans.
• LLMs can mimic descriptions of conscious experiences, leading to public confusion about agency and consciousness.
• The scientific community lacks consensus on the theoretical explanation of consciousness, complicating the understanding of LLM consciousness.
• Some scientists assume LLMs are not conscious, while others suggest the opposite, but these assumptions lack empirical evidence.
• Integrated Information Theory suggests consciousness could be common in any domain where information is integrated, but this claim is premature.
• Measuring consciousness remains a significant unresolved problem, crucial for both human and potential machine consciousness.
• Current cognitive neuroscience models have not identified specific cognitive functions that necessitate consciousness.
• The debate on LLM consciousness is stuck due to the lack of empirical methods and reliance on theoretical assumptions.
• The problem of determining consciousness in LLMs echoes similar debates about consciousness in various biological entities.
• Identifying whether consciousness is biological/structural or functional/computational is crucial for understanding LLM consciousness.
• The biological-functional distinction suggests consciousness is either tied to physical structures or functions.
• If consciousness depends on biological structures, LLMs will not be conscious unless instantiated in the 'right' material.
• If consciousness depends on functional properties, LLMs could be conscious if they run the 'right' software.
• The complexity aspect considers whether consciousness requires complex or simple structures/functions.
• Higher-order thought theory suggests consciousness may require metacognitive abilities, which LLMs currently lack.
• If consciousness is linked to simple functions, artificial systems might have been conscious long before LLMs.
• The complexity aspect also affects the biological view, with more complex structures implying fewer conscious species.
• The matrix approach segments the theoretical landscape into a two-by-two matrix, aiding in understanding LLM consciousness.
• The matrix offers a theory-neutral mapping of the possibility space for LLM consciousness.
• It is premature to draw conclusions about LLM consciousness, but the matrix may help parse incoming data.
• Until significant progress is made, drawing conclusions about LLM consciousness remains unscientific.
• The study discusses the holographic projection of representative information content.
• Tononi (2005) explores consciousness, information integration, and the brain in "Progress in Brain Research."
• Tononi et al. (2016) present Integrated Information Theory, linking consciousness to its physical substrate in "Nature Reviews Neuroscience."
• Wiese and Friston (2021) examine the neural correlates of consciousness under the free energy principle in "Philosophy and Mind Science."
• The authors declare no competing interests.
• Ethical approval was not required as the study did not involve human participants.
• Informed consent was not required as the study did not involve human participants.
• Springer Nature remains neutral regarding jurisdictional claims in published maps and institutional affiliations.
• The article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
• The license permits non-commercial use, sharing, distribution, and reproduction with appropriate credit to the original authors and source.
• Adapted material derived from the article cannot be shared under this license.
• Images or third-party material included in the article are covered by the article’s Creative Commons license unless otherwise indicated.
• For uses not permitted by statutory regulation or exceeding the license, permission must be obtained from the copyright holder.
• The article by Overgaard and Kirkeby-Hinrup clarifies conditions under which Large Language Models could be conscious.
• The article is published in "Humanities and Social Sciences Communications" in 2024.
• The DOI for the article is https://doi.org/10.1057/s41599-024-03553-w.