Related Experiment Video
Updated: May 16, 2025
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
466
Enhancing supermarket robot interaction: an equitable multi-level LLM conversational interface for handling diverse
Chandran Nandkumar1, Luka Peternel1
1Department of Cognitive Robotics, Delft University of Technology, Delft, Netherlands.
Frontiers in Robotics and AI
|May 14, 2025
Summary
This study introduces a new multi-Large Language Model (LLM) chatbot for supermarkets, outperforming GPT-4 Turbo in user satisfaction and efficiency. It also identifies OpenAI's Whisper as the top speech recognition model for diverse users.
Area of Science:
- Human-Computer Interaction
- Artificial Intelligence
- Robotics
Background:
- Current customizable systems like GPTs face challenges in response time, strategic control, and cost-efficiency for tailored applications.
- There is a need for equitable, efficient, and personalized conversational agents in retail environments.
Purpose of the Study:
- To design and evaluate a voice-based interface system for supermarket shoppers.
- To compare the accuracy of speech recognition technologies across genders and languages.
- To develop and assess a novel multi-LLM chatbot framework against a specialized GPT model.
Main Methods:
- Comparative analysis of four off-the-shelf speech recognition technologies (gender/language specific).
- Development and evaluation of a multi-LLM supermarket chatbot framework.
- Performance comparison using the Artificial Social Agent Questionnaire (ASAQ) and qualitative feedback.
- Method for supermarket robot navigation based on chatbot responses.
Main Results:
- OpenAI's Whisper demonstrated superior speech recognition accuracy across genders and languages.
- The proposed multi-LLM chatbot significantly outperformed the GPT-4 Turbo model in performance, user satisfaction, user-agent partnership, and self-image enhancement.
- All 13 evaluated aspects showed improvement, with statistical significance in four key areas.
Conclusions:
- A multi-LLM approach offers advantages over single, powerful models for specialized applications like supermarket voice interfaces.
- The developed system enhances user experience and can be integrated with robot navigation for product retrieval.
- This research advocates for the use of multiple specialized smaller models for improved efficiency and customization.
Related Concept Videos
01:22Multi-input and Multi-variable systems
90
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
In the absence...
90
02:16Stereotype Content Model
13.9K
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...
13.9K
01:19High-Level and Low-Level Awareness
229
Controlled processes in human consciousness represent high-alert mental states where individuals deliberately focus their attention on achieving specific goals. Controlled processes can be seen in situations like mastering new technology, where a person might become so absorbed that they ignore surrounding distractions. Such processes involve selective attention, requiring one to concentrate on particular elements of experience while disregarding others. These are governed by executive...
229
01:30Machines: Problem Solving II
270
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
270
01:27Levels of Communication II: Organizational, Public, and Group Dynamics
1.9K
Effective communication is the foundation of a good organization. Communication is the lifeblood of an organization that connects the group with messages. In an organization, communication occurs in upward, downward, and horizontal lines. Downward communication travels from the administrative and senior levels to the staff through official channels such as manuals, rules and regulations, and organizational charts. Staff members initiate upward communication, which is addressed to executives and...
1.9K
01:24Natural and Artificial Concepts
89
In psychology, concepts can be divided into two categories: natural and artificial. Natural concepts are formed through direct or indirect experiences. For example, consider the concept of snow. If you live in a place with regular snowfall, such as Essex Junction, Vermont, you know snow through direct experiences. You’ve seen it fall, touched it, shoveled it, and played in it. You recognize its texture, appearance, and even its smell. In contrast, if you live on an island like Saint...
89