Enhancing LLM-Based Human-Robot Interaction with Nuances for Diversity Awareness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grassi, Lucrezia, Recchiuto, Carmine Tommaso, Sgorbissa, Antonio
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916299885510656
author Grassi, Lucrezia
Recchiuto, Carmine Tommaso
Sgorbissa, Antonio
author_facet Grassi, Lucrezia
Recchiuto, Carmine Tommaso
Sgorbissa, Antonio
contents This paper presents a system for diversity-aware autonomous conversation leveraging the capabilities of large language models (LLMs). The system adapts to diverse populations and individuals, considering factors like background, personality, age, gender, and culture. The conversation flow is guided by the structure of the system's pre-established knowledge base, while LLMs are tasked with various functions, including generating diversity-aware sentences. Achieving diversity-awareness involves providing carefully crafted prompts to the models, incorporating comprehensive information about users, conversation history, contextual details, and specific guidelines. To assess the system's performance, we conducted both controlled and real-world experiments, measuring a wide range of performance indicators.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17531
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing LLM-Based Human-Robot Interaction with Nuances for Diversity Awareness
Grassi, Lucrezia
Recchiuto, Carmine Tommaso
Sgorbissa, Antonio
Robotics
Artificial Intelligence
Human-Computer Interaction
This paper presents a system for diversity-aware autonomous conversation leveraging the capabilities of large language models (LLMs). The system adapts to diverse populations and individuals, considering factors like background, personality, age, gender, and culture. The conversation flow is guided by the structure of the system's pre-established knowledge base, while LLMs are tasked with various functions, including generating diversity-aware sentences. Achieving diversity-awareness involves providing carefully crafted prompts to the models, incorporating comprehensive information about users, conversation history, contextual details, and specific guidelines. To assess the system's performance, we conducted both controlled and real-world experiments, measuring a wide range of performance indicators.
title Enhancing LLM-Based Human-Robot Interaction with Nuances for Diversity Awareness
topic Robotics
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2406.17531