多様性を考慮したLLMベースの人間-ロボット対話システム
Enhancing LLM-Based Human-Robot Interaction with Nuances for Diversity Awareness
大規模言語モデルを活用し、ユーザーの背景・性格・年齢・性別・文化などに応じて対話を適応させる多様性対応の自律対話システムを提案し、実験で評価した。
著者: Lucrezia Grassi, Carmine Tommaso Recchiuto, Antonio Sgorbissa
分類: cs.RO, cs.AI, cs.HC
原文アブストラクト
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.
