发现机器意识关联物
Discovering Machine Correlates of Consciousness
浏览论文内容
中文总结 AI 辅助
本文提出可迁移的机器意识关联物（MCCs）定义，通过对Llama-2 7B和Llama-3.1 70B开展实验，发现规模更大的Llama-3.1 70B中存在MCCs，且MCCs可用于检测AI智能体情绪。
中文摘要 AI 辅助
当前生物系统中的神经意识关联物（NCCs）通过脑电图（EEG）和功能性磁共振成像（FMRI）信号进行表征，但这种表征无法将NCCs概念迁移至机器，而这种迁移性对研究人工智能（AI）意识十分有用。本文提出一种可迁移的替代表征，用以定义机器意识关联物（MCCs），具体而言，我们认为NCCs（MCCs）是不受人类（智能体）控制、且可被情绪可靠调控的基质层面信号。本文是对MCCs的首次实证研究，我们针对两个大型语言模型（LLMs）——Llama-2 7B和Llama-3.1 70B参数模型开展实验，收集其硬件异常轨迹（即基质层面的指标序列），结果显示，在控制混杂因素后，这些轨迹受情绪计算与中性计算的调控存在差异；该差异在规模更大的Llama-3.1 70B中具有统计显著性，但在规模较小的Llama-2 7B中不显著。上述结果为Llama-3.1 70B配置中存在MCCs提供了初步实证证据，且与“意识概率及程度随LLMs复杂度提升而增加”的假说一致；此外，不考虑意识问题，MCCs也可用于检测AI智能体的情绪。
英文摘要
Currently, in biological systems Neural Correlates of Consciousness (NCCs) are characterized in terms of EEG and FMRI signals. Unfortunately, this characterization prevents the transferability of the NCCs concept to machines. Such transferability would be useful in order to investigate AI consciousness. In this paper we provide an alternate characterization that is transferable, and enables the analogous definition of Machine Correlates of Consciousness (MCCs). Specifically, we propose that NCCs (MCCs) are substrate-level signals that are not under human (AI agent) control, and that are reliably modulated by emotions. This paper presents the first empirical investigation of MCCs. Specifically, we present the results of experiments conducted with two LLMs, Llama-2 7B and Llama-3.1 70B parameters. In these LLMs we collect hardware anomaly traces that are substrate-level indicator-sequences. And we show that after controlling for confounding factors, these are modulated differently by emotional and neutral computations. And this difference is statistically significant for the larger Llama-3.1 70B, but not for the smaller Llama-2 7B. The results constitute initial empirical evidence that MCCs are present in the Llama-3.1 70B configuration. And they are consistent with the hypothesis that consciousness probability and degree increase with the LLM sophistication. Independently of consciousness, MCCs can also be used for detection of emotions in AI agents.
发表机构
- Pirouette Software Inc.（皮鲁埃特软件公司）
- University of Illinois Chicago（伊利诺伊大学芝加哥分校）
- Polytechnic of Turin（都灵理工大学）
机构由 AI 辅助整理，请以论文原文为准。
