解决人工通用智能对齐问题的功能性语境、以观察者为中心、量子力学和神经符号方法:通过交叉计算心理神经科学和 LLM 架构实现安全人工智能的新兴心智理论

IF 2.1 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY
Darren J. Edwards
{"title":"解决人工通用智能对齐问题的功能性语境、以观察者为中心、量子力学和神经符号方法:通过交叉计算心理神经科学和 LLM 架构实现安全人工智能的新兴心智理论","authors":"Darren J. Edwards","doi":"10.3389/fncom.2024.1395901","DOIUrl":null,"url":null,"abstract":"There have been impressive advancements in the field of natural language processing (NLP) in recent years, largely driven by innovations in the development of transformer-based large language models (LLM) that utilize “attention.” This approach employs masked self-attention to establish (via similarly) different positions of tokens (words) within an inputted sequence of tokens to compute the most appropriate response based on its training corpus. However, there is speculation as to whether this approach alone can be scaled up to develop emergent artificial general intelligence (AGI), and whether it can address the alignment of AGI values with human values (called the alignment problem). Some researchers exploring the alignment problem highlight three aspects that AGI (or AI) requires to help resolve this problem: (1) an interpretable values specification; (2) a utility function; and (3) a dynamic contextual account of behavior. Here, a neurosymbolic model is proposed to help resolve these issues of human value alignment in AI, which expands on the transformer-based model for NLP to incorporate symbolic reasoning that may allow AGI to incorporate perspective-taking reasoning (i.e., resolving the need for a dynamic contextual account of behavior through deictics) as defined by a multilevel evolutionary and neurobiological framework into a functional contextual post-Skinnerian model of human language called “Neurobiological and Natural Selection Relational Frame Theory” (<jats:italic>N</jats:italic>-Frame). It is argued that this approach may also help establish a comprehensible value scheme, a utility function by expanding the expected utility equation of behavioral economics to consider functional contextualism, and even an observer (or witness) centric model for consciousness. Evolution theory, subjective quantum mechanics, and neuroscience are further aimed to help explain consciousness, and possible implementation within an LLM through correspondence to an interface as suggested by <jats:italic>N</jats:italic>-Frame. This argument is supported by the computational level of hypergraphs, relational density clusters, a conscious quantum level defined by QBism, and real-world applied level (human user feedback). It is argued that this approach could enable AI to achieve consciousness and develop deictic perspective-taking abilities, thereby attaining human-level self-awareness, empathy, and compassion toward others. Importantly, this consciousness hypothesis can be directly tested with a significance of approximately 5-sigma significance (with a 1 in 3.5 million probability that any identified AI-conscious observations in the form of a collapsed wave form are due to chance factors) through double-slit intent-type experimentation and visualization procedures for derived perspective-taking relational frames. Ultimately, this could provide a solution to the alignment problem and contribute to the emergence of a theory of mind (ToM) within AI.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A functional contextual, observer-centric, quantum mechanical, and neuro-symbolic approach to solving the alignment problem of artificial general intelligence: safe AI through intersecting computational psychological neuroscience and LLM architecture for emergent theory of mind\",\"authors\":\"Darren J. Edwards\",\"doi\":\"10.3389/fncom.2024.1395901\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"There have been impressive advancements in the field of natural language processing (NLP) in recent years, largely driven by innovations in the development of transformer-based large language models (LLM) that utilize “attention.” This approach employs masked self-attention to establish (via similarly) different positions of tokens (words) within an inputted sequence of tokens to compute the most appropriate response based on its training corpus. However, there is speculation as to whether this approach alone can be scaled up to develop emergent artificial general intelligence (AGI), and whether it can address the alignment of AGI values with human values (called the alignment problem). Some researchers exploring the alignment problem highlight three aspects that AGI (or AI) requires to help resolve this problem: (1) an interpretable values specification; (2) a utility function; and (3) a dynamic contextual account of behavior. Here, a neurosymbolic model is proposed to help resolve these issues of human value alignment in AI, which expands on the transformer-based model for NLP to incorporate symbolic reasoning that may allow AGI to incorporate perspective-taking reasoning (i.e., resolving the need for a dynamic contextual account of behavior through deictics) as defined by a multilevel evolutionary and neurobiological framework into a functional contextual post-Skinnerian model of human language called “Neurobiological and Natural Selection Relational Frame Theory” (<jats:italic>N</jats:italic>-Frame). It is argued that this approach may also help establish a comprehensible value scheme, a utility function by expanding the expected utility equation of behavioral economics to consider functional contextualism, and even an observer (or witness) centric model for consciousness. Evolution theory, subjective quantum mechanics, and neuroscience are further aimed to help explain consciousness, and possible implementation within an LLM through correspondence to an interface as suggested by <jats:italic>N</jats:italic>-Frame. This argument is supported by the computational level of hypergraphs, relational density clusters, a conscious quantum level defined by QBism, and real-world applied level (human user feedback). It is argued that this approach could enable AI to achieve consciousness and develop deictic perspective-taking abilities, thereby attaining human-level self-awareness, empathy, and compassion toward others. Importantly, this consciousness hypothesis can be directly tested with a significance of approximately 5-sigma significance (with a 1 in 3.5 million probability that any identified AI-conscious observations in the form of a collapsed wave form are due to chance factors) through double-slit intent-type experimentation and visualization procedures for derived perspective-taking relational frames. Ultimately, this could provide a solution to the alignment problem and contribute to the emergence of a theory of mind (ToM) within AI.\",\"PeriodicalId\":12363,\"journal\":{\"name\":\"Frontiers in Computational Neuroscience\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2024-08-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Computational Neuroscience\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.3389/fncom.2024.1395901\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MATHEMATICAL & COMPUTATIONAL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Computational Neuroscience","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3389/fncom.2024.1395901","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

近年来,自然语言处理(NLP)领域取得了令人瞩目的进步,这主要得益于利用 "注意力 "开发基于转换器的大型语言模型(LLM)的创新成果。这种方法采用掩蔽式自我注意力,(通过类似的方式)在输入的标记词序列中确定标记词(单词)的不同位置,从而根据其训练语料库计算出最合适的反应。然而,有人猜测,仅靠这种方法是否能扩大规模,开发出新兴的人工通用智能(AGI),以及是否能解决 AGI 价值与人类价值的一致性问题(称为一致性问题)。一些探索一致性问题的研究人员强调,AGI(或人工智能)需要以下三个方面来帮助解决这个问题:(1)可解释的价值规范;(2)效用函数;(3)行为的动态背景说明。在此,我们提出了一个神经符号模型,以帮助解决人工智能中的这些人类价值一致性问题,该模型扩展了基于变压器的 NLP 模型,纳入了符号推理,可使 AGI 将多层次进化和神经生物学框架所定义的视角推理(即通过 deictics 解决对行为动态语境说明的需求)纳入名为 "神经生物学和自然选择关系框架理论"(N-Frame)的后斯金纳人类语言功能语境模型。本文认为,这种方法还有助于建立一个可理解的价值体系,通过扩展行为经济学的预期效用方程来考虑功能语境主义,从而建立效用函数,甚至建立一个以观察者(或目击者)为中心的意识模型。进化论、主观量子力学和神经科学的目标是进一步帮助解释意识,并通过与 N-Frame所建议的界面对应,在LLM中实现意识。这一论点得到了超图计算层面、关系密度集群、QBism定义的意识量子层面以及现实世界应用层面(人类用户反馈)的支持。有观点认为,这种方法可以让人工智能实现意识,并发展出脱敏透视能力,从而达到人类水平的自我意识、同理心和对他人的同情心。重要的是,通过双缝意向型实验和衍生透视关系框架的可视化程序,这一意识假设可以直接进行测试,其显著性约为 5 西格玛(350 万分之一的概率是由于偶然因素造成的)。最终,这将为对齐问题提供一个解决方案,并有助于在人工智能中出现心智理论(ToM)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A functional contextual, observer-centric, quantum mechanical, and neuro-symbolic approach to solving the alignment problem of artificial general intelligence: safe AI through intersecting computational psychological neuroscience and LLM architecture for emergent theory of mind
There have been impressive advancements in the field of natural language processing (NLP) in recent years, largely driven by innovations in the development of transformer-based large language models (LLM) that utilize “attention.” This approach employs masked self-attention to establish (via similarly) different positions of tokens (words) within an inputted sequence of tokens to compute the most appropriate response based on its training corpus. However, there is speculation as to whether this approach alone can be scaled up to develop emergent artificial general intelligence (AGI), and whether it can address the alignment of AGI values with human values (called the alignment problem). Some researchers exploring the alignment problem highlight three aspects that AGI (or AI) requires to help resolve this problem: (1) an interpretable values specification; (2) a utility function; and (3) a dynamic contextual account of behavior. Here, a neurosymbolic model is proposed to help resolve these issues of human value alignment in AI, which expands on the transformer-based model for NLP to incorporate symbolic reasoning that may allow AGI to incorporate perspective-taking reasoning (i.e., resolving the need for a dynamic contextual account of behavior through deictics) as defined by a multilevel evolutionary and neurobiological framework into a functional contextual post-Skinnerian model of human language called “Neurobiological and Natural Selection Relational Frame Theory” (N-Frame). It is argued that this approach may also help establish a comprehensible value scheme, a utility function by expanding the expected utility equation of behavioral economics to consider functional contextualism, and even an observer (or witness) centric model for consciousness. Evolution theory, subjective quantum mechanics, and neuroscience are further aimed to help explain consciousness, and possible implementation within an LLM through correspondence to an interface as suggested by N-Frame. This argument is supported by the computational level of hypergraphs, relational density clusters, a conscious quantum level defined by QBism, and real-world applied level (human user feedback). It is argued that this approach could enable AI to achieve consciousness and develop deictic perspective-taking abilities, thereby attaining human-level self-awareness, empathy, and compassion toward others. Importantly, this consciousness hypothesis can be directly tested with a significance of approximately 5-sigma significance (with a 1 in 3.5 million probability that any identified AI-conscious observations in the form of a collapsed wave form are due to chance factors) through double-slit intent-type experimentation and visualization procedures for derived perspective-taking relational frames. Ultimately, this could provide a solution to the alignment problem and contribute to the emergence of a theory of mind (ToM) within AI.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Frontiers in Computational Neuroscience
Frontiers in Computational Neuroscience MATHEMATICAL & COMPUTATIONAL BIOLOGY-NEUROSCIENCES
CiteScore
5.30
自引率
3.10%
发文量
166
审稿时长
6-12 weeks
期刊介绍: Frontiers in Computational Neuroscience is a first-tier electronic journal devoted to promoting theoretical modeling of brain function and fostering interdisciplinary interactions between theoretical and experimental neuroscience. Progress in understanding the amazing capabilities of the brain is still limited, and we believe that it will only come with deep theoretical thinking and mutually stimulating cooperation between different disciplines and approaches. We therefore invite original contributions on a wide range of topics that present the fruits of such cooperation, or provide stimuli for future alliances. We aim to provide an interactive forum for cutting-edge theoretical studies of the nervous system, and for promulgating the best theoretical research to the broader neuroscience community. Models of all styles and at all levels are welcome, from biophysically motivated realistic simulations of neurons and synapses to high-level abstract models of inference and decision making. While the journal is primarily focused on theoretically based and driven research, we welcome experimental studies that validate and test theoretical conclusions. Also: comp neuro
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信