LILITH：基于化学信号的开发型模块化大语言模型架构（论文已被作者撤回）
Lilith: Developmental Modular LLMs with Chemical Signaling
AI 导读
Mohid Farooqi 提出的 LILITH 论文已被作者撤回，作者表示这是其不再认可的早期初步工作。该架构构想将思维、记忆、感觉和调节等不同脑区建模为专门的大语言模型模块，通过类神经递质网络的基于 token 的通信协议交互，并采用未训练模型经模拟生活经历和进化优化的发育式训练，以 Integrated Information Theory 指标研究意识涌现。
正文 · 原文
This paper has been withdrawn by Mohid Farooqi
No PDF available, click to view other formats
Abstract: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.
| Comments: | This paper has been withdrawn by the author as it represents early, preliminary work that the author no longer endorses. |
| Subjects: | Neurons and Cognition (q-bio.NC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2507.04575 [q-bio.NC] |
| (or arXiv:2507.04575v2 [q-bio.NC] for this version) | |
| https://doi.org/10.48550/arXiv.2507.04575 arXiv-issued DOI via DataCite |
Submission history
From: Mohid Farooqi [view email]
[v1]
Sun, 6 Jul 2025 23:18:51 UTC (17 KB)
[v2]
Wed, 11 Nov 2026 14:42:42 UTC (1 KB) (withdrawn)
来源：arXiv cs.AI · arxiv.org