Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.04575 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918085174231040 |
|---|---|
| author | Farooqi, Mohid Comas-Leon, Alejandro |
| author_facet | Farooqi, Mohid Comas-Leon, Alejandro |
| contents | Current paradigms in Artificial Intelligence rely on layers of feedforward networks which model brain activity at the neuronal level. We conjecture that expanding to the level of multiple brain regions with chemical signaling may be a productive step toward understanding the emergence of consciousness. We propose LILITH, a novel architecture that combines developmental training of modular language models with brain-inspired token-based communication protocols, mirroring chemical signaling in the brain. Our approach models distinct brain regions as specialized LLM modules including thinking, memory, sensory, and regulatory components that communicate through emergent token-based signaling protocols analogous to neurotransmitter networks. Unlike traditional pre-trained systems, LILITH would employ developmental training where untrained LLM architectures learn through simulated life experiences, developing communication pathways and cognitive abilities through environmental interaction and evolutionary optimization. This framework would enable direct empirical investigation of consciousness emergence using Integrated Information Theory metrics while providing unprecedented insight into inter-module signaling patterns during development. By optimizing for consciousness emergence rather than task performance, LILITH could provide insight into different emergent phenomena at multiple levels of neural correlates, contrasting neuronal-level processing with multi-region coordination dynamics. The goal of this paper is to put the idea forward while recognizing the substantial challenges in implementing such a system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04575 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lilith: Developmental Modular LLMs with Chemical Signaling Farooqi, Mohid Comas-Leon, Alejandro Neurons and Cognition Artificial Intelligence Current paradigms in Artificial Intelligence rely on layers of feedforward networks which model brain activity at the neuronal level. We conjecture that expanding to the level of multiple brain regions with chemical signaling may be a productive step toward understanding the emergence of consciousness. We propose LILITH, a novel architecture that combines developmental training of modular language models with brain-inspired token-based communication protocols, mirroring chemical signaling in the brain. Our approach models distinct brain regions as specialized LLM modules including thinking, memory, sensory, and regulatory components that communicate through emergent token-based signaling protocols analogous to neurotransmitter networks. Unlike traditional pre-trained systems, LILITH would employ developmental training where untrained LLM architectures learn through simulated life experiences, developing communication pathways and cognitive abilities through environmental interaction and evolutionary optimization. This framework would enable direct empirical investigation of consciousness emergence using Integrated Information Theory metrics while providing unprecedented insight into inter-module signaling patterns during development. By optimizing for consciousness emergence rather than task performance, LILITH could provide insight into different emergent phenomena at multiple levels of neural correlates, contrasting neuronal-level processing with multi-region coordination dynamics. The goal of this paper is to put the idea forward while recognizing the substantial challenges in implementing such a system. |
| title | Lilith: Developmental Modular LLMs with Chemical Signaling |
| topic | Neurons and Cognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.04575 |