期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到4篇文章
< 1 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Prosocial behavior in Large Language Models:Value alignment and afective mechanisms 认领 引用 被引量：1
1
作者 Hao LIU Yu LEI Zhen WU 《Science China(Technological Sciences)》 SCIE EI CAS CSCD 2025年第8期185-199,共15页
While advanced Large Language Models(LLMs)can simulate human-like prosocial behaviors,the degree to which they align with human prosocial values and the underlying afective mechanisms remain unclear.This study address... While advanced Large Language Models(LLMs)can simulate human-like prosocial behaviors,the degree to which they align with human prosocial values and the underlying afective mechanisms remain unclear.This study addressed these gaps using the third-party punishment(TPP)paradigm,comparing LLM agents(GPT and DeepSeek series)with human participants(n=100).The LLM agents(n=500,100 agents per model)were one-to-one constructed based on the demographic and psychological features of human participants.Prompt engineering was employed to initiate TPP games and record punitive decisions and afective responses in LLM agents.Results revealed that:(1)GPT-4o,DeepSeek-V3,and DeepSeek-R1 models demonstrated stronger fairness value alignment,choosing punitive options more frequently than humans in TPP games;(2)all LLMs replicated the human pathway from unfairness through negative afective response to punitive decisions,with stronger mediation efects of negative emotions observed in DeepSeek models than GPT models;(3)only DeepSeek-R1 exhibited the human-like positive feedback loop from previous punitive decisions to positive afective feedback and subsequent punitive choices;(4)most LLMs(excluding GPT-3.5)showed signifcant representational similarity to human afect-decision patterns;(5)notably,all LLMs displayed rigid afective dynamics,characterized by lower afective variability and higher afective inertia than the fexible,contextsensitive fuctuations observed in humans.These fndings highlight notable advances in prosocial value alignment but underscore the necessity to enhance their afective dynamics to foster robust,adaptive prosocial LLMs.Such advancements could not only accelerate LLMs'alignment with human values but also provide empirical support for the broader applicability of prosocial theories to LLM agents. 展开更多
关键词 Large Language Models value alignment prosocial behavior affective mechanisms
暂未订购 下载PDF
A Mathematical Formulation of AGI in the(C,U,V)Framework 认领 引用
2
作者 Di He Cong Fang +3 位作者 Yisen Wang Yujia Peng Yizhou Wang Song-Chun Zhu 《Engineering》 SCIE EI CSCD 2026年第7期166-180,共15页
This article seeks to explore a general formulation of artificial general intelligence(AGI)under a unified framework that defines AGI agents as points in a joint(C,U,V)space.An agent is characterized by three componen... This article seeks to explore a general formulation of artificial general intelligence(AGI)under a unified framework that defines AGI agents as points in a joint(C,U,V)space.An agent is characterized by three components:①a cognitive architecture C,which represents the modules(mathematical functions)inside the agent’s mind,as well as the connections and communication protocols between these modules,including the theory of mind(ToM);②a set of potential functions U,which represents the skills of perception,cognition,and planning(e.g.,a potential function can be a neural network trained for visual object recognition,or embodied motion planning);and③a set of value functions V,which includes the agent’s urges,preferences,and social affections,as well as benefits for individual agents or a group of agents.In this setting,“intelligence”is defined as a wide range of phenomena exhibited by agents when they interact with complex environments(i.e.,physical intelligence)and other agents(i.e.,social intelligence).Given an initial point in the(C,U,V)space,an agent can explore new V-dimensions,which in turn drives the acquisition and learning of skills by enabling the learning of new potential functions U in the environment and by updating the cognitive model.We have developed a Tong test as a benchmark and evaluation criteria:An agent that has reached the human level(C,U,V)is called a“Tong Agent.”The convergence of this process defines the limits of the agent’s evolution;we name this the“stopping problem”of Tong Agents,based on the analogy of the halting problem in a Turing machine. 展开更多
关键词 Artificial general intelligence Value alignment Machine learning Evolutionary learning
暂未订购 下载PDF
通智测试——基于动态具身物理社会交互环境的通用人工智能测试 认领 引用 被引量：8
3
作者 Yujia Peng Jiaheng Han +7 位作者 Zhenliang Zhang Lifeng Fan Tengyu Liu Siyuan Qi Xue Feng Yuxi Ma Yizhou Wang Song-Chun Zhu 《Engineering》 SCIE EI CAS CSCD 2024年第3期12-22,共11页
The release of the generative pre-trained transformer(GPT)series has brought artificial general intelligence(AGI)to the forefront of the artificial intelligence(AI)field once again.However,the questions of how to defi... The release of the generative pre-trained transformer(GPT)series has brought artificial general intelligence(AGI)to the forefront of the artificial intelligence(AI)field once again.However,the questions of how to define and evaluate AGI remain unclear.This perspective article proposes that the evaluation of AGI should be rooted in dynamic embodied physical and social interactions(DEPSI).More specifically,we propose five critical characteristics to be considered as AGI benchmarks and suggest the Tong test as an AGI evaluation system.The Tong test describes a value-and ability-oriented testing system that delineates five levels of AGI milestones through a virtual environment with DEPSI,allowing for infinite task generation.We contrast the Tong test with classical AI testing systems in terms of various aspects and propose a systematic evaluation system to promote standardized,quantitative,and objective benchmarks and evaluation of AGI. 展开更多
关键词 Artificial general intelligence Artificial intelligence benchmark Artificial intelligence evaluation Embodied artificial intelligence Value alignment Turing test Causality
暂未订购 下载PDF
Exploring Educator Values Alignment Strategies in an Intervention Context: The Emergence of the Beacon Strategy 认领 引用 被引量：3
4
作者 Penelope Kalogeropoulos James Anthony Russo Philip Clarkson 《ECNU Review of Education》 2021年第2期327-348,共22页
Purpose:The purpose of this paper is to explore whether the four value alignment strategies available to educators(Scaffolding,Balancing,Intervention,and Refuge)previously identified in the mathematics education liter... Purpose:The purpose of this paper is to explore whether the four value alignment strategies available to educators(Scaffolding,Balancing,Intervention,and Refuge)previously identified in the mathematics education literature comprehensively capture educator value alignment strategies in an in terve ntion con text.Design/Approach/Methods:To this end,we analyse semi-structured interview data with two teacher-leaders involved in the Getting Ready in Numeracy(G.R.I.N.)intervention program through a value alignment lens.Findings:We ascertain that a fifth strategy,the Beacon strategy,is needed to describe the range of value alignment strategies employed by educators in the GRI.N.program.The Beacon strategy involves the educator digging in and reasserting their expectations until the student behaves in a manner that aligns with the educator's values.In part it invoIves the educator being able to recognize their own values and clearly communicating these values to students.O rigin al ity/Value:This article further explores strategies that educators have at their disposal for aligning their values with those of their students.The uncovering of the Beacon strategy is particularly valuable as it suggests that educators could be purposefully pursuing value alignment even when they do not appear to take any active steps to move further towards their students'sets of values. 展开更多
关键词 Engagement values values alignment
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈