Jove
Visualize
联系我们

相关概念视频

Behavior Modification01:21

Behavior Modification

125
Behavioral approaches have often been criticized for ignoring mental processes and focusing solely on observable behavior. However, these approaches provide an optimistic perspective for individuals seeking to change their behaviors. Rather than concentrating on intrinsic personality traits, behavioral approaches suggest that even longstanding habits can be modified by changing the reward contingencies that maintain them.
A real-world application of operant conditioning principles is applied...
125

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Incipient Constituents: Phonesthemes Facilitate Word Processing in English.

Open mind : discoveries in cognitive science·2026
Same author

A dual-functional Terbium-organic framework fluorescence sensor for ratiometric identification of bilirubin and visualization detection of phenylglyoxylic acid.

Analytica chimica acta·2026
Same author

Self-adaptive cleaning technology for artillery laser ignition windows based on current feedback.

Scientific reports·2026
Same author

Speaker effects in language comprehension: An integrative model of language and speaker processing.

Psychonomic bulletin & review·2026
Same author

Perspective alignment in dialogue: The role of interlocutor's linguistic competence and communicative goals.

Cognition·2026
Same author

MOF-Derived Carbon-Anchored Cu<sub>2</sub>Se/MnSe Heterointerfacial Nanoparticles for Enhanced Lithium Storage via Synergistic Interface Effects.

Molecules (Basel, Switzerland)·2026
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关实验视频

Updated: Jun 4, 2025

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.1K

MacBehaviour:一个用于在大型语言模型上的行为实验的R包.

Xufeng Duan1, Shixuan Li2, Zhenguang G Cai3,4

  • 1Department of Linguistics and Modern Languages, The Chinese University of Hong Kong, Hong Kong, China. xufeng.duan@link.cuhk.edu.hk.

Behavior research methods
|December 18, 2024
PubMed
概括

研究人员开发了"MacBehaviour",这是一个R包,用于在心理实验中研究大型语言模型 (LLM). 这个工具简化了LLM的行为研究,揭示了类似人类的性别推断,从像GPT-3.5 Turbo.这样的模型中的名字中推断出来.

关键词:
进行实验和试验.大型语言模型.机器行为 机器行为在R包中,R包是R包.

更多相关视频

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

500

相关实验视频

Last Updated: Jun 4, 2025

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.1K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

500

科学领域:

  • 认知科学 认知科学
  • 人工智能的人工智能
  • 计算语言学 计算语言学

背景情况:

  • 大型语言模型 (LLM) 和LLM驱动的聊天机器人越来越多地使用心理学实验方法进行研究.
  • 现有的研究通常将LLM视为参与者,因此需要有效的行为实验工具.

研究的目的:

  • 引入"MacBehaviour",一个R包,旨在简化使用LLMs进行心理实验的过程.
  • 为研究人员提供一个用户友好的工具,用于实验设计,刺激呈现,模型行为操纵和数据记录.

主要方法:

  • 开发了"MacBehaviour" R包,可以与100多个LLM (例如GPT,Claude,Gemini,Llama) 进行交互.
  • 实验设置,刺激传递,响应记录和代币概率分析的实现功能.
  • 通过对GPT-3.5 Turbo,Llama-2-7b-chat-hf和Vicuna-1.5-13b进行三次实验来验证该包.

主要成果:

  • "MacBehaviour"套件成功促进了LLM的行为实验.
  • 对声音与性别关联研究的复制表明,经过测试的LLM表现出类似人类的倾向,根据语音学推断基于新个人名的性别.
  • LLM 显示了一致的模式,反映了人类在性别关联中的认知偏见.

结论:

  • "MacBehaviour"是一个有价值的,用户友好的R包,简化和标准化机器行为研究.
  • 该套餐提高了研究LLM认知和行为的研究人员的可访问性.
  • 这些发现证实了LLM对类似人类的语音基于性别推断的能力,进步了我们对AI认知的理解.