相关实验视频

Updated: Jun 3, 2025

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

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

Published on: December 6, 2024

以儿童为中心的机器人对话系统:微调大型语言模型,以更好地理解发言和交互

Da-Young Kim^1,2, Hyo Jeong Lym¹, Hanna Lee¹

¹Human-Robot Interaction Center, Korea Institute of Robotics & Technology Convergence (KIRO), Pohang 37553, Republic of Korea.

Sensors (Basel, Switzerland)

|January 8, 2025

概括

这项研究通过微调大型语言模型 (LLM) 来增强儿童机器人交互的对话系统,以更好地理解儿童独特的语言模式,改善对话参与.

科学领域:

人工智能的人工智能
人与计算机的交互
计算语言学计算语言学

背景情况:

目前的对话系统,包括大型语言模型 (LLM),难以准确地解释儿童独特的语言特征,如不完整的语法和错误发音.
有效的儿童机器人交互需要能够理解儿童发言意图的对话系统,类似于人类的理解.

研究的目的:

为基于LLM的对话系统开发一个微调方法,以提高他们解释儿童发言意图的能力.
为了使儿童和机器人之间能够进行自然和自适应的语言互动,即使使用非标准的语言.

主要方法:

提出了使用两种类型数据的微调方法:LLM-人类判断差异和交互式响应数据.
根据LLM和人类判断差异数据,在LLM和人类对儿童反应的解释有所不同的情况下,这些数据被捕获.
交互式响应数据由机器人响应组成,根据儿童的发言意图量身定制,由LLM生成.

主要成果:

开发了一个精心调整的对话系统,能够像人类一样解释儿童的发言.
该系统表现出适应性反应,有效处理语法不完整性和错误发音.
使用机器人社会属性尺度 (RoSAS) 和敏感度和特异性平均值 (SSA) 度量的人类评估验证了系统的性能.

结论:

拟议的微调方法大大提高了基于LLM的对话系统在解释儿童发言意图方面的表现.
该系统在儿童机器人场景中促进了更自然的语言交互,适应了语言变异.
这种方法弥合了LLM能力和人类层面对儿童语言的理解之间的差距.

关键词:

儿童机器人互动对话系统对话系统人与机器人的互动社交机器人社交机器人

更多相关视频

Using the Visual World Paradigm to Study Sentence Comprehension in Mandarin-Speaking Children with Autism

Using the Visual World Paradigm to Study Sentence Comprehension in Mandarin-Speaking Children with Autism

Published on: October 3, 2018

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Published on: January 5, 2024

相关概念视频

Language Development

Language Development

Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...

Stereotype Content Model

Stereotype Content Model

The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...