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

TL;DR

This paper introduces a diversity-aware conversational system using large language models that adapts to individual differences and cultural backgrounds, enhancing human-robot interaction.

Contribution

It presents a novel framework for diversity-aware dialogue generation in LLM-based systems, incorporating detailed user information and structured prompts for improved personalization.

Findings

Effective diversity-aware responses generated in experiments

Improved adaptation to individual and cultural differences

Validated system performance through real-world testing

Abstract

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.